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

    Neuronpedia

    INDEX
    Explanations

    start

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     обла
    -0.07
    weights
    -0.07
     perverse
    -0.07
     زندگی
    -0.06
    ельно
    -0.06
    middlewares
    -0.06
    piar
    -0.06
    quip
    -0.06
     grado
    -0.06
    /{$
    -0.06
    POSITIVE LOGITS
     Rolling
    0.07
     Majority
    0.07
     IF
    0.07
     solar
    0.06
    rench
    0.06
     entitlement
    0.06
     hart
    0.06
    /Admin
    0.06
     ACPI
    0.06
     hall
    0.06
    Act Density 0.003%

    No Known Activations