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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating positive experiences or feelings

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

    in fact, you can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.61
     Biôgrafia
    -0.56
    setVerticalGroup
    -0.51
    IsMutable
    -0.48
     simplifié
    -0.47
    ThroughAttribute
    -0.46
     مرئيه
    -0.45
    новништво
    -0.44
     Signalez
    -0.44
    findpost
    -0.41
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.50
     nawr
    0.49
    ]")]
    0.48
    клопе
    0.47
     كومونز
    0.45
    inerja
    0.42
     تضيفلها
    0.42
    quehanna
    0.41
     Dane
    0.40
    forChild
    0.40
    Act Density 0.009%

    No Known Activations