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

    Neuronpedia

    INDEX
    Explanations

    science and foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     қала
    -0.08
     suggests
    -0.08
     period
    -0.07
    羊
    -0.07
     redemption
    -0.07
     könnt
    -0.07
     gian
    -0.07
    秋
    -0.07
    agal
    -0.07
     derby
    -0.07
    POSITIVE LOGITS
     fundamentally
    0.09
    _indexes
    0.08
     hingegen
    0.08
    oi
    0.08
    indexes
    0.08
    Indexes
    0.08
     exposição
    0.08
    segue
    0.07
     মত
    0.07
     सार
    0.07
    Act Density 0.126%

    No Known Activations