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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atility
    -0.07
    配上
    -0.07
    _bag
    -0.07
     barracks
    -0.07
    ภาพย
    -0.07
     Jama
    -0.06
    lıkları
    -0.06
     tossing
    -0.06
     economists
    -0.06
     Hak
    -0.06
    POSITIVE LOGITS
    Padding
    0.07
    :path
    0.07
     hsv
    0.07
    ipl
    0.07
    花纹
    0.07
    _MODAL
    0.07
     opens
    0.07
     vagina
    0.06
    Options
    0.06
    pressed
    0.06
    Act Density 0.043%

    No Known Activations