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

    Neuronpedia

    INDEX
    Explanations

    import collections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ds
    -0.07
     Pruitt
    -0.07
    みたい
    -0.07
    もない
    -0.06
     FB
    -0.06
     Dou
    -0.06
     Boh
    -0.06
    ุก
    -0.06
     pie
    -0.06
     Bart
    -0.06
    POSITIVE LOGITS
     Darth
    0.07
     출
    0.07
    .tar
    0.07
    .soft
    0.06
    스테
    0.06
    _operand
    0.06
    .animations
    0.06
     znač
    0.06
    대학
    0.06
    _Address
    0.06
    Act Density 0.008%

    No Known Activations