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

    Neuronpedia

    INDEX
    Explanations

    _modules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    -0.07
    惕
    -0.07
    それは
    -0.07
    (am
    -0.06
    同時
    -0.06
     hashtags
    -0.06
    异味
    -0.06
     firstname
    -0.06
    אמת
    -0.06
     việc
    -0.06
    POSITIVE LOGITS
    丛林
    0.07
    female
    0.07
    _patient
    0.07
    accur
    0.07
     Lover
    0.07
     ré
    0.07
    极
    0.07
    _FIRE
    0.06
    耠
    0.06
    	Int
    0.06
    Act Density 0.027%

    No Known Activations