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

    Neuronpedia

    INDEX
    Explanations

    J

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vault
    -0.07
    SOURCE
    -0.06
     Hudson
    -0.06
     Oven
    -0.06
     Horizon
    -0.06
    ,↵↵
    -0.06
    usion
    -0.06
     Void
    -0.06
     Mata
    -0.06
     iki
    -0.06
    POSITIVE LOGITS
    .symmetric
    0.07
     حالة
    0.07
    λύ
    0.07
     cómo
    0.06
     laden
    0.06
    .nextSibling
    0.06
    لیم
    0.06
     pist
    0.06
    Authentication
    0.06
     blockIdx
    0.06
    Act Density 0.002%

    No Known Activations