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

    Neuronpedia

    INDEX
    Explanations

    Legal cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Allocator
    -0.06
    ucha
    -0.06
    ormal
    -0.06
    -summary
    -0.06
    .Detail
    -0.06
    .readline
    -0.06
    Match
    -0.06
     restricting
    -0.06
     přek
    -0.06
    _signal
    -0.06
    POSITIVE LOGITS
     [*
    0.07
     دریافت
    0.07
    pack
    0.07
     Tristan
    0.06
    思想
    0.06
    σίας
    0.06
     riot
    0.06
    貼
    0.06
    ENCY
    0.06
     traceback
    0.06
    Act Density 0.014%

    No Known Activations