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

    Neuronpedia

    INDEX
    Explanations

    expressing opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’un
    -0.07
    κος
    -0.07
    ід
    -0.07
     quand
    -0.06
    *>::
    -0.06
    pad
    -0.06
     Outer
    -0.06
     дополнитель
    -0.06
    风
    -0.06
     phản
    -0.06
    POSITIVE LOGITS
    sdale
    0.06
     Busty
    0.06
    영상
    0.06
     metaData
    0.06
     Bundesliga
    0.06
     hesitation
    0.06
     bills
    0.06
    .bo
    0.06
    _room
    0.06
    idebar
    0.06
    Act Density 0.001%

    No Known Activations