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

    Neuronpedia

    INDEX
    Explanations

    informative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >An
    -0.06
     miraculous
    -0.06
    apiro
    -0.06
     Everyone
    -0.06
     Gauge
    -0.06
    unused
    -0.06
    ----------</
    -0.06
     firmalar
    -0.06
     Ein
    -0.05
     contexts
    -0.05
    POSITIVE LOGITS
    AVOR
    0.08
    Ngh
    0.07
    ENCIL
    0.07
    >'.$
    0.07
     perks
    0.07
    alore
    0.06
     секрет
    0.06
    صر
    0.06
     Beispiel
    0.06
     confirmation
    0.06
    Act Density 0.009%

    No Known Activations