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

    Neuronpedia

    INDEX
    Explanations

    Canvas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Al
    -0.08
    酗
    -0.07
    Indian
    -0.07
     cen
    -0.07
     Pret
    -0.07
     Nord
    -0.07
    <C
    -0.07
    +E
    -0.07
     thở
    -0.07
     الولايات
    -0.07
    POSITIVE LOGITS
    珛
    0.07
    .untracked
    0.07
    产出
    0.07
     iOS
    0.07
    业务
    0.07
     abortion
    0.07
     Management
    0.06
     economy
    0.06
    剩下
    0.06
    geben
    0.06
    Act Density 0.000%

    No Known Activations