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

    Neuronpedia

    INDEX
    Explanations

    establish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cows
    -0.07
    ooting
    -0.07
    itto
    -0.07
     caching
    -0.07
    _filter
    -0.06
    icts
    -0.06
     DataView
    -0.06
     Pik
    -0.06
    boards
    -0.06
     delay
    -0.06
    POSITIVE LOGITS
    reds
    0.06
    \Traits
    0.06
    .pool
    0.06
     oğ
    0.06
    สต
    0.06
     nét
    0.06
    ิญญ
    0.06
    してる
    0.06
     여
    0.06
    Tambah
    0.06
    Act Density 0.013%

    No Known Activations