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

    Neuronpedia

    INDEX
    Explanations

    _get

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <K
    -0.07
    纷
    -0.07
    vehicles
    -0.07
     Jury
    -0.07
    .setY
    -0.07
     ف
    -0.07
    Routine
    -0.06
    atisfied
    -0.06
    ctrine
    -0.06
     Taj
    -0.06
    POSITIVE LOGITS
     recommand
    0.07
     và
    0.07
     embedded
    0.07
    معرف
    0.07
     hilarious
    0.07
    זל
    0.06
     travers
    0.06
    فض
    0.06
    咣
    0.06
     qed
    0.06
    Act Density 0.001%

    No Known Activations