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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    肃
    -0.07
     नई
    -0.07
     TILE
    -0.06
     interracial
    -0.06
    QUIRE
    -0.06
    __))
    -0.06
    称
    -0.06
    cosa
    -0.06
     enfrent
    -0.06
     visceral
    -0.06
    POSITIVE LOGITS
    ampling
    0.08
     Μά
    0.07
    rite
    0.07
    ape
    0.07
    -wrapper
    0.06
    ρε
    0.06
    考
    0.06
    yan
    0.06
     proposes
    0.06
    �
    0.06
    Act Density 0.042%

    No Known Activations