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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ER
    -0.07
    Scaler
    -0.07
     patriarch
    -0.07
    _orig
    -0.07
    .decorators
    -0.06
    ']↵↵
    -0.06
     Bread
    -0.06
    :block
    -0.06
    保存
    -0.06
    /MIT
    -0.06
    POSITIVE LOGITS
     propensity
    0.07
    ocytes
    0.06
     Pak
    0.06
    _CHOICES
    0.06
    ophon
    0.06
    _attach
    0.06
    تباط
    0.06
    yet
    0.06
    ारण
    0.06
     {{--<
    0.06
    Act Density 0.001%

    No Known Activations