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

    Neuronpedia

    INDEX
    Explanations

    percentages and proportions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ++↵
    -0.08
    ::*;↵
    -0.08
     Ici
    -0.08
     আজ
    -0.08
    ::*;↵↵
    -0.08
     Tonight
    -0.08
     dunia
    -0.08
    remo
    -0.07
    আজ
    -0.07
    mee
    -0.07
    POSITIVE LOGITS
     규모
    0.09
     sized
    0.09
     хэмжээ
    0.08
    -sized
    0.08
     boutique
    0.08
     உர
    0.08
     көлем
    0.08
     independently
    0.08
     bewust
    0.07
    _arch
    0.07
    Act Density 0.063%

    No Known Activations