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

    Neuronpedia

    INDEX
    Explanations

    squares and exponents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ارتباط
    -0.08
     Alert
    -0.08
     �
    -0.08
     opted
    -0.08
     entertained
    -0.08
     تماس
    -0.07
    unterricht
    -0.07
    manız
    -0.07
    lhs
    -0.07
    Alert
    -0.07
    POSITIVE LOGITS
    倍
    0.08
     પ્રમાણ
    0.08
     halves
    0.08
    -thirds
    0.07
    」に
    0.07
     exponent
    0.07
     बनने
    0.07
     legal
    0.07
    隆
    0.07
     प्रमाण
    0.07
    Act Density 0.014%

    No Known Activations