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

    Neuronpedia

    INDEX
    Explanations

    -Control

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doldur
    -0.06
    änd
    -0.06
    $j
    -0.06
    ंगठन
    -0.06
    รษ
    -0.06
    源
    -0.06
     cosy
    -0.06
    玛
    -0.06
    _regularizer
    -0.05
     มห
    -0.05
    POSITIVE LOGITS
    	Debug
    0.07
     Promotion
    0.07
     ww
    0.07
     Carb
    0.07
    ByID
    0.06
     Permission
    0.06
    REAT
    0.06
    tp
    0.06
     Continent
    0.06
     watering
    0.06
    Act Density 0.001%

    No Known Activations