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

    Neuronpedia

    INDEX
    Explanations

    references to learning and knowledge

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

    know something about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geschehen
    -0.31
     Völker
    -0.28
     Gastgeber
    -0.28
     Gästen
    -0.27
    ofür
    -0.27
    ).
    -0.26
    際は
    -0.26
     for
    -0.26
     SHER
    -0.26
     förra
    -0.25
    POSITIVE LOGITS
    ChildScrollView
    0.82
    featureID
    0.77
    parsedMessage
    0.73
    bitField
    0.73
    transQ
    0.72
    ScopeManager
    0.68
    Tikang
    0.65
     nahilalakip
    0.64
    vician
    0.63
     gyhoeddwyd
    0.63
    Act Density 0.030%

    No Known Activations