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

    Neuronpedia

    INDEX
    Explanations

    legal/technical discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	stage
    -0.07
    otre
    -0.06
    眾
    -0.06
    _descr
    -0.06
     tutte
    -0.06
     interracial
    -0.06
    ۲۰۰
    -0.06
    OutOfRange
    -0.06
    (draw
    -0.06
     Stripe
    -0.06
    POSITIVE LOGITS
    �체
    0.08
     atm
    0.07
     Alejandro
    0.07
     kn
    0.07
    arence
    0.06
     JText
    0.06
     гру
    0.06
    .annotations
    0.06
     click
    0.06
    abl
    0.06
    Act Density 0.000%

    No Known Activations