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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and references to reasoning or justification

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

    conditional clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.37
    **/
    -0.33
     zvuky
    -0.32
    經過
    -0.31
    `,
    -0.30
     confirmed
    -0.30
     INS
    -0.30
     Comprometido
    -0.30
     giudi
    -0.29
     tapasztal
    -0.29
    POSITIVE LOGITS
    ########.
    0.56
    ViewImports
    0.55
     للاسماء
    0.54
    تقاوى
    0.54
     Biôgrafia
    0.53
    WireFormatLite
    0.50
    :+:
    0.50
     Administrativna
    0.48
     CURIAM
    0.48
    hichever
    0.47
    Act Density 0.388%

    No Known Activations