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

    Neuronpedia

    INDEX
    Explanations

    code, errors, unusual text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /bg
    -0.07
     Kab
    -0.07
     Lud
    -0.07
     Ordered
    -0.07
    控制
    -0.07
    (func
    -0.07
    _outputs
    -0.06
     toujours
    -0.06
     PROC
    -0.06
    	UPROPERTY
    -0.06
    POSITIVE LOGITS
    omination
    0.07
    ologies
    0.06
    ैय
    0.06
    innamon
    0.06
     mentoring
    0.06
     지나
    0.06
    اط
    0.06
    olo
    0.06
     сест
    0.06
    ParameterValue
    0.06
    Act Density 0.000%

    No Known Activations