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

    Neuronpedia

    INDEX
    Explanations

    math and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lust
    -0.07
    ��
    -0.07
     iPod
    -0.07
    ości
    -0.07
    ⵉ
    -0.07
     nackte
    -0.07
    inspace
    -0.07
    奇特
    -0.06
    newline
    -0.06
    ulner
    -0.06
    POSITIVE LOGITS
     Smy
    0.07
    (configuration
    0.07
     défin
    0.07
     consideration
    0.07
    omp
    0.07
    �
    0.06
     Farms
    0.06
     explor
    0.06
    Version
    0.06
     важ
    0.06
    Act Density 0.247%

    No Known Activations