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

    Neuronpedia

    INDEX
    Explanations

    protected

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ERRUPT
    -0.07
    .dep
    -0.07
    _val
    -0.07
    стер
    -0.07
    MMdd
    -0.07
     streams
    -0.07
    clidean
    -0.07
     company
    -0.07
    plx
    -0.06
     town
    -0.06
    POSITIVE LOGITS
    的进步
    0.08
    扪
    0.07
     Ksi
    0.07
    最后一
    0.07
     psychosis
    0.07
    公证
    0.06
    @Before
    0.06
    不多
    0.06
    ('"
    0.06
     الح
    0.06
    Act Density 0.029%

    No Known Activations