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

    Neuronpedia

    INDEX
    Explanations

    good

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     testCase
    -0.07
     key
    -0.07
    县政府
    -0.07
    遊
    -0.07
     ammonia
    -0.07
     Мне
    -0.06
     Rip
    -0.06
     sav
    -0.06
    ণ
    -0.06
    renal
    -0.06
    POSITIVE LOGITS
     equipped
    0.08
     perpetrator
    0.07
    .capacity
    0.07
     trader
    0.07
     founded
    0.07
    遏制
    0.07
     newsletters
    0.07
     loans
    0.07
     ・
    0.07
    _PHONE
    0.07
    Act Density 0.022%

    No Known Activations