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

    Neuronpedia

    INDEX
    Explanations

    gl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    2
    -0.08
    _task
    -0.08
    From
    -0.08
     retire
    -0.08
    หมวด
    -0.07
    晡
    -0.07
     
    -0.07
     coeff
    -0.07
    throw
    -0.07
     tempt
    -0.07
    POSITIVE LOGITS
    איכות
    0.08
     pronounced
    0.08
    -directed
    0.07
     quảng
    0.07
    ᐡ
    0.07
     BJP
    0.07
    	buttons
    0.07
    プログ
    0.07
    执导
    0.07
     מר
    0.06
    Act Density 0.032%

    No Known Activations