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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pch
    -0.06
    _sale
    -0.06
     sábado
    -0.06
     تغییر
    -0.06
    -Mar
    -0.06
     shocking
    -0.06
    Pid
    -0.06
     hare
    -0.06
     rừng
    -0.06
    КИ
    -0.06
    POSITIVE LOGITS
     decay
    0.07
    .toDouble
    0.07
     spotting
    0.07
     maintenance
    0.07
    ımlı
    0.07
     페
    0.06
     worlds
    0.06
     /*----------------------------------------------------------------
    0.06
    [token
    0.06
    ظˆ
    0.06
    Act Density 0.000%

    No Known Activations