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

    Neuronpedia

    INDEX
    Explanations

    Code defines and macros

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Senior
    -0.07
    _Handler
    -0.07
    ysl
    -0.07
     conventional
    -0.06
    ává
    -0.06
    .toJSONString
    -0.06
    _micro
    -0.06
    .cluster
    -0.06
     frü
    -0.06
     Te
    -0.06
    POSITIVE LOGITS
    ματο
    0.07
     thúc
    0.07
    رده
    0.07
    攝
    0.06
    ...,
    0.06
    ламент
    0.06
    جن
    0.06
    伝
    0.06
     จำก
    0.06
     vyžad
    0.06
    Act Density 0.008%

    No Known Activations