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

    Neuronpedia

    INDEX
    Explanations

    null

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     classe
    -0.07
     Huyện
    -0.07
     appetite
    -0.07
     구글
    -0.07
     maker
    -0.06
    ascii
    -0.06
    علام
    -0.06
    -mini
    -0.06
    Raises
    -0.06
    _constants
    -0.06
    POSITIVE LOGITS
     Hamas
    0.07
    0.07
     nouvel
    0.07
    erv
    0.06
    arged
    0.06
     출연
    0.06
    BLE
    0.06
    asured
    0.06
    AGE
    0.06
    τής
    0.06
    Act Density 0.003%

    No Known Activations