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

    Neuronpedia

    INDEX
    Explanations

    limitations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bart
    -0.08
    rases
    -0.06
    .isNotBlank
    -0.06
     mensen
    -0.06
     SCH
    -0.06
    enga
    -0.06
    .segments
    -0.06
     phrase
    -0.06
    )+"
    -0.06
     Salt
    -0.06
    POSITIVE LOGITS
    FFT
    0.07
     DataManager
    0.07
    _rgb
    0.06
     gyr
    0.06
    ibox
    0.06
     handleSubmit
    0.06
    gni
    0.06
    ุด
    0.06
    erala
    0.06
    ього
    0.06
    Act Density 0.001%

    No Known Activations