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

    Neuronpedia

    INDEX
    Explanations

    HTML or XML tags related to dependencies

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

    XML dependency lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vähän
    -0.32
    快
    -0.29
    gentes
    -0.28
     pří
    -0.27
     הכ
    -0.27
     čty
    -0.27
     nahilalakip
    -0.26
     dintre
    -0.26
     Pingback
    -0.26
    ifikationer
    -0.25
    POSITIVE LOGITS
     myſelf
    0.68
     itſelf
    0.67
     Diſ
    0.65
     ProtoMessage
    0.64
     Perſ
    0.63
     Reſ
    0.62
    AxisAlignment
    0.61
    styleType
    0.59
     Eſ
    0.59
     themſelves
    0.57
    Act Density 0.000%

    No Known Activations