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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wash
    -0.07
    Battery
    -0.07
    mlx
    -0.06
    Her
    -0.06
     Valor
    -0.06
    259
    -0.06
    worker
    -0.06
    PRIVATE
    -0.06
    _canvas
    -0.06
    repair
    -0.06
    POSITIVE LOGITS
     ΠΡ
    0.07
    thur
    0.07
    NOWLED
    0.07
     быстро
    0.07
     сим
    0.07
     μη
    0.07
     ness
    0.07
     BroadcastReceiver
    0.07
     καν
    0.06
    _SAN
    0.06
    Act Density 0.047%

    No Known Activations