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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    แล
    -0.08
    暑
    -0.07
     Sequ
    -0.07
     Meetings
    -0.07
    _distribution
    -0.07
     meisje
    -0.07
     eleven
    -0.07
    ……………………
    -0.07
    .Action
    -0.07
     למנ
    -0.07
    POSITIVE LOGITS
    🍴
    0.07
    atican
    0.06
    ßen
    0.06
    덖
    0.06
    jącym
    0.06
    reset
    0.06
    \v
    0.06
     greeted
    0.06
    حيا
    0.06
    瀏
    0.06
    Act Density 0.021%

    No Known Activations