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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating kindness or supportive actions

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

    calvin, brady, that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ExecuteAsync
    -0.42
    ContentAsync
    -0.37
    AutoScaleMode
    -0.33
     satisfactor
    -0.30
     following
    -0.30
    JoinTable
    -0.30
    Quali
    -0.30
     princí
    -0.30
     constitutional
    -0.29
     szükség
    -0.29
    POSITIVE LOGITS
    Билгалдахарш
    0.70
     surla
    0.69
    thâu
    0.68
     AssemblyCulture
    0.62
     yaiba
    0.62
    rungsseite
    0.62
    évaluateur
    0.59
    __).
    0.59
     الرياضيه
    0.57
    erweise
    0.57
    Act Density 0.051%

    No Known Activations