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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     후기
    -0.06
    Returns
    -0.06
     {↵↵
    -0.06
    uye
    -0.06
     vanished
    -0.06
    ambio
    -0.06
    H
    -0.06
     dispenser
    -0.06
    ünün
    -0.06
    Func
    -0.06
    POSITIVE LOGITS
     tailored
    0.06
     τά
    0.06
     kullan
    0.06
    (OP
    0.06
    crafted
    0.06
     OP
    0.06
    (extension
    0.06
    owntown
    0.06
     кри
    0.06
     стандарт
    0.06
    Act Density 0.013%

    No Known Activations