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

    Neuronpedia

    INDEX
    Explanations

    references to corporations and their public statements regarding controversial social issues

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

    negative descriptions or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    progressDialog
    -0.34
     Entsch
    -0.32
    แต
    -0.31
    terima
    -0.31
    來說
    -0.30
     commenting
    -0.29
     COMMENT
    -0.29
    ConfigureAwait
    -0.28
     Comment
    -0.28
     conseguir
    -0.28
    POSITIVE LOGITS
    AutoField
    0.67
     Мексичка
    0.65
    \{\\
    0.64
    kuuta
    0.61
    دانشنامهٔ
    0.57
    Aiheesta
    0.56
    ThroughAttribute
    0.54
    addGap
    0.54
     autorytatywna
    0.54
     estekak
    0.54
    Act Density 0.032%

    No Known Activations