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

    Neuronpedia

    INDEX
    Explanations

    references to the impact of small contributions or efforts on larger outcomes

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

    small amounts or differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mayor
    -0.39
    outchouc
    -0.39
     Twice
    -0.38
    Mayor
    -0.37
    :^{
    -0.37
    sbericht
    -0.36
    sofa
    -0.35
    スピーカー
    -0.35
     Мексичка
    -0.35
     MAYOR
    -0.34
    POSITIVE LOGITS
     AssemblyCulture
    0.61
    ########.
    0.57
    providedIn
    0.51
     small
    0.50
    inSlope
    0.50
    TagMode
    0.48
     <<<<<<<<<<<<<<
    0.48
     작
    0.47
    Small
    0.46
     piccoli
    0.46
    Act Density 0.037%

    No Known Activations