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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _estimators
    -0.08
    .exception
    -0.07
    GPC
    -0.07
    encial
    -0.07
    .enum
    -0.06
    /bash
    -0.06
     Akron
    -0.06
    elig
    -0.06
    .say
    -0.06
     někdy
    -0.06
    POSITIVE LOGITS
    ände
    0.07
     vocational
    0.06
    omens
    0.06
    мот
    0.06
    landing
    0.06
    changed
    0.06
     bü
    0.06
    нивер
    0.06
    竞
    0.06
     Womens
    0.06
    Act Density 0.038%

    No Known Activations