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

    Neuronpedia

    INDEX
    Explanations

    qualifiers and descriptors that indicate emphasis or importance

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

    made [descriptor] [outcome]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.56
     NSCoder
    -0.50
    ThroughAttribute
    -0.46
     BoxDecoration
    -0.45
    monials
    -0.43
    tonode
    -0.43
    tgär
    -0.42
    secuencias
    -0.42
    tahui
    -0.41
     Réponses
    -0.41
    POSITIVE LOGITS
     made
    0.94
     make
    0.93
     Make
    0.88
    make
    0.84
     Making
    0.84
    made
    0.84
     making
    0.82
    Make
    0.82
    Making
    0.82
     Made
    0.79
    Act Density 0.039%

    No Known Activations