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

    Neuronpedia

    INDEX
    Explanations

    code security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Plane
    -0.07
    罂
    -0.07
    _CRYPTO
    -0.07
    din
    -0.06
    习惯了
    -0.06
    怀抱
    -0.06
    营养
    -0.06
    .LOGIN
    -0.06
     Sicher
    -0.06
    CHANGE
    -0.06
    POSITIVE LOGITS
    找出
    0.08
    代理人
    0.08
     Según
    0.07
    isers
    0.07
    JWT
    0.07
     recurrent
    0.07
     terminated
    0.07
    Year
    0.06
    aturday
    0.06
    ions
    0.06
    Act Density 0.065%

    No Known Activations