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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to official approval or authorization

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

    approval or penalty sanction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    didSet
    -0.41
    Ằ
    -0.38
    alagi
    -0.33
     Widodo
    -0.33
    <bos>
    -0.32
    __":
    -0.30
     Wä
    -0.30
    wv
    -0.30
     Käufer
    -0.30
    rrggbb
    -0.29
    POSITIVE LOGITS
     sanction
    1.82
     sanctioned
    1.67
     sanctions
    1.34
     Sanctions
    1.34
     санк
    1.05
     Sanctuary
    0.96
    san
    0.81
     Sank
    0.79
    sanitize
    0.75
     Sancti
    0.75
    Act Density 0.006%

    No Known Activations