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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thịt
    -0.07
    。而
    -0.06
    爸
    -0.06
     preferably
    -0.06
     Wrapped
    -0.06
     horrend
    -0.06
    ‌آ
    -0.06
    itas
    -0.06
     coisa
    -0.06
    printer
    -0.06
    POSITIVE LOGITS
     Cuba
    0.07
    .this
    0.06
    bone
    0.06
    ANCELED
    0.06
     Removes
    0.06
     bombers
    0.06
     QMessageBox
    0.06
    执行
    0.06
    .setWindowTitle
    0.06
    VENT
    0.06
    Act Density 0.000%

    No Known Activations