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

    Neuronpedia

    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Page
    -0.07
    ymous
    -0.07
    _username
    -0.07
    ätig
    -0.07
    пуск
    -0.07
    速度
    -0.07
    ῶ
    -0.06
    ��
    -0.06
    .Func
    -0.06
    mpjes
    -0.06
    POSITIVE LOGITS
    GeV
    0.07
     NEG
    0.06
     rip
    0.06
     Integrity
    0.06
    再造
    0.06
     ctl
    0.06
    Ţ
    0.06
     deliberate
    0.06
     CAST
    0.06
     В
    0.06
    Act Density 0.015%

    No Known Activations