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
     rebut
    -0.07
    games
    -0.07
    PRINT
    -0.07
    avior
    -0.07
    poz
    -0.07
     europé
    -0.06
    blem
    -0.06
    ósito
    -0.06
    asurement
    -0.06
     Break
    -0.06
    POSITIVE LOGITS
     ativ
    0.07
    وليو
    0.07
    orea
    0.06
    ября
    0.06
    .getAs
    0.06
    精品
    0.06
    ัตร
    0.06
    +s
    0.06
    341
    0.06
     socialist
    0.06
    Act Density 0.000%

    No Known Activations