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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    assin
    -0.07
    .PackageManager
    -0.07
    .provider
    -0.07
    Score
    -0.07
    oreach
    -0.07
    raits
    -0.07
    edy
    -0.06
     рассказ
    -0.06
     whom
    -0.06
     інформа
    -0.06
    POSITIVE LOGITS
    ーフ
    0.06
     主
    0.06
     істор
    0.06
    document
    0.06
    _pool
    0.06
     tapered
    0.06
    �
    0.06
    (bytes
    0.06
    airie
    0.06
     coin
    0.06
    Act Density 0.004%

    No Known Activations