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

    Neuronpedia

    INDEX
    Explanations

    CSS normalize/reset

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     العمر
    -0.08
    煞
    -0.07
    -fire
    -0.07
     UserRole
    -0.06
     الاست
    -0.06
    天生
    -0.06
    慆
    -0.06
    oled
    -0.06
     irradi
    -0.06
    uele
    -0.06
    POSITIVE LOGITS
    通讯员
    0.08
    _ty
    0.08
    줌
    0.07
    مائ
    0.07
     journalists
    0.07
     fifteen
    0.07
     hızlı
    0.07
     defenders
    0.07
    .this
    0.07
    مم
    0.06
    Act Density 0.000%

    No Known Activations