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

    Neuronpedia

    INDEX
    Explanations

    appear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	count
    -0.07
    rowsing
    -0.07
    elder
    -0.07
    spark
    -0.06
    #!/
    -0.06
    系列
    -0.06
    ryptography
    -0.06
    dw
    -0.06
    vfs
    -0.06
    _kw
    -0.06
    POSITIVE LOGITS
    draulic
    0.07
     fif
    0.07
    炸
    0.06
     partir
    0.06
    Empleado
    0.06
     wondered
    0.06
    BTN
    0.06
    ают
    0.06
     Quando
    0.06
    ın
    0.06
    Act Density 0.001%

    No Known Activations