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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⅽ
    -0.74
    compromised
    -0.73
     dumped
    -0.72
     notable
    -0.71
    dotte
    -0.71
     włas
    -0.70
     noteworthy
    -0.69
    サロン
    -0.69
    retweeted
    -0.69
    詹
    -0.68
    POSITIVE LOGITS
     изменения
    0.69
    CHF
    0.69
    ۶
    0.68
    煌
    0.67
    Rules
    0.67
     PILOT
    0.66
    きら
    0.66
    OST
    0.66
     AKP
    0.66
    ണ്
    0.65
    Act Density 0.046%

    No Known Activations