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

    Neuronpedia

    INDEX
    Explanations

    surprise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chemistry
    -0.07
    绩
    -0.06
     Там
    -0.06
     sciences
    -0.06
     Chemistry
    -0.06
    useum
    -0.06
    _expr
    -0.06
     attracts
    -0.06
    Compute
    -0.06
     Toxic
    -0.06
    POSITIVE LOGITS
     attendant
    0.06
    グル
    0.06
     clinics
    0.06
     Claud
    0.06
    .PREFERRED
    0.06
     spoj
    0.06
     배우
    0.06
    ิลป
    0.06
     приготов
    0.06
     gord
    0.06
    Act Density 0.053%

    No Known Activations