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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     navigating
    -0.07
     chặt
    -0.07
    che
    -0.06
    dělení
    -0.06
     SHIFT
    -0.06
     Assembly
    -0.06
    odes
    -0.06
    _C
    -0.06
     مورد
    -0.06
     nüfus
    -0.06
    POSITIVE LOGITS
     可
    0.06
    <vector
    0.06
    選手
    0.06
     ERR
    0.06
     texas
    0.06
     cinemat
    0.06
     polít
    0.06
     Rand
    0.06
    현
    0.05
     sut
    0.05
    Act Density 0.012%

    No Known Activations