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

    Neuronpedia

    INDEX
    Explanations

    inspiration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     файл
    -0.08
    ✙
    -0.07
     Saying
    -0.07
     RFC
    -0.07
     CZ
    -0.07
    욯
    -0.07
    瑷
    -0.07
    📛
    -0.07
    (QIcon
    -0.07
    stdout
    -0.07
    POSITIVE LOGITS
    Become
    0.08
    若干
    0.07
     vô
    0.07
    avourites
    0.07
    :on
    0.06
    .mac
    0.06
    릴
    0.06
    ritos
    0.06
    izacion
    0.06
    ennes
    0.06
    Act Density 0.063%

    No Known Activations