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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     keyPressed
    -0.07
     H�
    -0.07
     spokesman
    -0.07
     編
    -0.07
    -basic
    -0.06
    _salt
    -0.06
     Basic
    -0.06
    ССР
    -0.06
     rigor
    -0.06
    Ｋ
    -0.06
    POSITIVE LOGITS
    Last
    0.07
     Bibli
    0.07
     commonly
    0.06
    ��
    0.06
     conclude
    0.06
     intercept
    0.06
     Anton
    0.06
     audio
    0.06
    ĩa
    0.06
     tão
    0.06
    Act Density 0.038%

    No Known Activations