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

    Neuronpedia

    INDEX
    Explanations

    the presence of semicolons in code snippets

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

    conversational boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.97
    uxxxx
    -0.82
     utafitiHapana
    -0.75
     kasarigan
    -0.75
     незавершена
    -0.74
    parsedMessage
    -0.73
    AutoScaleMode
    -0.70
     zwiſchen
    -0.69
    EDEFAULT
    -0.69
    참고
    -0.68
    POSITIVE LOGITS
    .
    0.38
     Heart
    0.34
    ことができました
    0.34
    paravant
    0.34
    mặt
    0.34
     previously
    0.33
     Discovery
    0.31
    quién
    0.31
     Previously
    0.30
     matrícula
    0.29
    Act Density 0.003%

    No Known Activations