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

    Neuronpedia

    INDEX
    Explanations

    html

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cover
    -0.07
     málo
    -0.06
    되었습니다
    -0.06
     Morales
    -0.06
     понять
    -0.06
     kaps
    -0.06
    азвание
    -0.06
     bursting
    -0.06
    ozí
    -0.06
    (resultSet
    -0.06
    POSITIVE LOGITS
    ATHER
    0.07
    ンス
    0.07
    σεων
    0.06
    cb
    0.06
    rf
    0.06
    acter
    0.06
    ��
    0.06
     Echo
    0.06
    ymbols
    0.06
    _auth
    0.06
    Act Density 0.034%

    No Known Activations