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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Skills
    -0.07
    (py
    -0.07
    parity
    -0.07
    JNI
    -0.06
    (Html
    -0.06
    ОР
    -0.06
    lies
    -0.06
     chaque
    -0.06
     Cp
    -0.06
    HSV
    -0.06
    POSITIVE LOGITS
    _MetaData
    0.07
     Tud
    0.07
    .AddTransient
    0.07
     Dodd
    0.06
     pensions
    0.06
    ^
    0.06
     trov
    0.06
    }";↵↵
    0.06
     cocos
    0.06
     verr
    0.06
    Act Density 0.000%

    No Known Activations