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

    Neuronpedia

    INDEX
    Explanations

    circuit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gestalten
    -0.08
    Plano
    -0.08
    Declare
    -0.08
    Blueprint
    -0.08
    uss
    -0.07
     Dolly
    -0.07
    _REAL
    -0.07
     പ്രസ
    -0.07
    pp
    -0.07
     ਭ
    -0.07
    POSITIVE LOGITS
     death
    0.07
     கடந்த
    0.07
    ாமல்
    0.07
     установлен
    0.07
     xmin
    0.07
     cere
    0.07
     chronology
    0.07
     mse
    0.07
     сопротив
    0.07
    edin
    0.07
    Act Density 0.002%

    No Known Activations