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

    Neuronpedia

    INDEX
    Explanations

    criteria for structured data or code snippets

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

    start of user turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.66
     للمعارف
    -0.61
    XmlAccessType
    -0.60
    ViewInit
    -0.59
     resourceCulture
    -0.59
    <?
    -0.55
    ValueStyle
    -0.54
     ब्रेकडाउन
    -0.54
     nonatomic
    -0.52
     <<<<<<<<<<<<<<
    -0.52
    POSITIVE LOGITS
     Meksiku
    0.37
     podjet
    0.35
     povezave
    0.34
     bezeichneter
    0.34
    ksessa
    0.34
     táctil
    0.33
     suplementos
    0.33
     resolución
    0.32
     psicológica
    0.32
     segredo
    0.32
    Act Density 0.000%

    No Known Activations