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

    Neuronpedia

    INDEX
    Explanations

    magic tricks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Player
    -0.07
     yetiş
    -0.07
     otev
    -0.06
    .infinity
    -0.06
     Mara
    -0.06
    _manual
    -0.06
     patriotic
    -0.06
     Sonia
    -0.06
    Various
    -0.06
    ryptography
    -0.06
    POSITIVE LOGITS
    hashed
    0.06
     تیم
    0.06
    .password
    0.06
     applies
    0.06
    sembl
    0.06
     pitching
    0.06
     khám
    0.06
     Ding
    0.06
     impr
    0.06
     Combined
    0.06
    Act Density 0.005%

    No Known Activations