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

    Neuronpedia

    INDEX
    Explanations

    bold formatting and special symbols

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

    features and settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     оригіналу
    -0.35
    原始内容存档于
    -0.33
     Füßen
    -0.31
    횟
    -0.30
    consulté
    -0.30
     This
    -0.30
    enderror
    -0.30
     étions
    -0.30
    uidado
    -0.30
     With
    -0.29
    POSITIVE LOGITS
    <strong>
    0.82
    <em>
    0.81
    <u>
    0.73
    <i>
    0.67
    <b>
    0.66
    /**
    0.62
     autorytatywna
    0.59
    //
    0.57
     müſſen
    0.55
    truly
    0.53
    Act Density 0.062%

    No Known Activations