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

    Neuronpedia

    INDEX
    Explanations

    personal introductions and expressions of self-identity

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

    enjoy, love, serve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.92
     noDo
    -0.82
     autorytatywna
    -0.82
    RegressionTest
    -0.73
    NewUrlParser
    -0.60
    Filmografia
    -0.57
     Pergamon
    -0.57
    IContainer
    -0.57
    ariste
    -0.57
    StoreMessageInfo
    -0.56
    POSITIVE LOGITS
    发表于
    0.34
    новништво
    0.31
     ModelExpression
    0.31
     Wel
    0.30
     Buck
    0.30
     TH
    0.29
     el
    0.28
    aarrggbb
    0.27
     صوتيه
    0.27
     Th
    0.26
    Act Density 0.053%

    No Known Activations