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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Auswahl
    -0.06
    ISTR
    -0.06
    iddy
    -0.06
     arter
    -0.06
    道
    -0.06
    .decor
    -0.06
    LR
    -0.06
     dial
    -0.06
    ichi
    -0.06
     Lighting
    -0.06
    POSITIVE LOGITS
    _CLOSE
    0.07
     dlouho
    0.07
    ABCDEFGHI
    0.07
    追
    0.06
    арів
    0.06
    .updateDynamic
    0.06
     barracks
    0.06
    _sun
    0.06
     direccion
    0.06
     Plat
    0.06
    Act Density 0.002%

    No Known Activations