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

    Neuronpedia

    INDEX
    Explanations

    ARS

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    只要
    -0.07
     بودن
    -0.07
     Gle
    -0.06
     Thu
    -0.06
    Invoice
    -0.06
     codes
    -0.06
    134
    -0.06
     descriptions
    -0.06
    MaxLength
    -0.06
     Roulette
    -0.06
    POSITIVE LOGITS
     reactionary
    0.07
     ambush
    0.07
     pong
    0.07
    uters
    0.07
     υπό
    0.06
    -bal
    0.06
    .objects
    0.06
    дал
    0.06
     πρα
    0.06
    irez
    0.06
    Act Density 0.001%

    No Known Activations