Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    structured formats and numerical values typically used in scientific or technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Inside parentheses, often with numbers or symbols

    np_acts-logits-general · gemini-2.0-flash

    sections, methods, materials, study

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rptr
    -0.40
    Gweler
    -0.40
    Rptr
    -0.39
     conmigo
    -0.39
     Beine
    -0.37
    XmlAccessType
    -0.36
    otros
    -0.36
     Hände
    -0.36
     Spitze
    -0.35
     Stirn
    -0.34
    POSITIVE LOGITS
    setVerticalGroup
    0.73
     CreateTagHelper
    0.63
     للاسماء
    0.63
     MainAxisSize
    0.60
     autorytatywna
    0.55
    endregion
    0.53
    */),
    0.51
    twimg
    0.51
    transQ
    0.50
    SequentialGroup
    0.50
    Act Density 0.338%

    No Known Activations