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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to academic or professional contexts

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

    before prepositions or punctuation

    np_acts-logits-general · gemini-2.0-flash

    legal and non-legal terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -1.03
    UserScript
    -0.99
     NSCoder
    -0.91
     photolibrary
    -0.89
    MLLoader
    -0.87
     صوتيه
    -0.86
     tfsi
    -0.86
    InputTagHelper
    -0.85
    elemField
    -0.85
     $_(
    -0.84
    POSITIVE LOGITS
    .
    1.18
    ,
    1.15
    ),
    0.96
    ?
    0.94
    )
    0.94
    ).
    0.93
     to
    0.84
    ;
    0.80
     in
    0.80
     for
    0.77
    Act Density 2.857%

    No Known Activations