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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency or commonality

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

    common usage or occurrence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hjælp
    -0.53
     BorderSide
    -0.52
    DoubleQuotes
    -0.51
    enumi
    -0.50
    AutoField
    -0.49
     hjelp
    -0.44
    存于互联网档案馆
    -0.44
    JZ
    -0.42
     this
    -0.42
    ródło
    -0.42
    POSITIVE LOGITS
    requently
    0.82
     frequently
    0.82
    frequently
    0.79
    marily
    0.76
     routinely
    0.73
     commonly
    0.71
     frecuentemente
    0.68
    typically
    0.67
     infrequently
    0.66
    quently
    0.66
    Act Density 0.009%

    No Known Activations