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

    Neuronpedia

    INDEX
    Explanations

    available

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Battery
    -0.07
     absorbing
    -0.07
    وزارة
    -0.07
     pueda
    -0.07
    arith
    -0.07
    Sources
    -0.07
    غار
    -0.07
    尻
    -0.07
    commit
    -0.07
    자
    -0.07
    POSITIVE LOGITS
     found
    0.07
    序幕
    0.07
     pelic
    0.07
     Bloc
    0.06
    痔
    0.06
    _cr
    0.06
    Ⲕ
    0.06
    实务
    0.06
    ucha
    0.06
    搭配
    0.06
    Act Density 0.008%

    No Known Activations