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

    Neuronpedia

    INDEX
    Explanations

    preferences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Emmanuel
    -0.07
     boil
    -0.07
    apiKey
    -0.06
    เตร
    -0.06
     Idol
    -0.06
    算
    -0.06
    andler
    -0.06
     Marilyn
    -0.06
    _org
    -0.06
     sanitize
    -0.06
    POSITIVE LOGITS
    ướng
    0.06
    щают
    0.06
    Thank
    0.06
     rk
    0.06
     tv
    0.06
     فقد
    0.06
     poorest
    0.06
    thetic
    0.06
    社会
    0.06
    홈
    0.06
    Act Density 0.113%

    No Known Activations