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

    Neuronpedia

    INDEX
    Explanations

    code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    少
    -0.07
    odox
    -0.06
    _proxy
    -0.06
     dwelling
    -0.06
     tire
    -0.06
    _lineno
    -0.06
     poetic
    -0.06
    遍
    -0.06
    BuildContext
    -0.06
     NDP
    -0.06
    POSITIVE LOGITS
     эконом
    0.07
    Sign
    0.06
     оборуд
    0.06
     tại
    0.06
     steel
    0.06
    련
    0.06
     satış
    0.06
     корист
    0.06
     WEIGHT
    0.06
     простран
    0.06
    Act Density 0.000%

    No Known Activations