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

    Neuronpedia

    INDEX
    Explanations

    **

    np_max-act · gemini-2.0-flash

    The neuron activates on instances of the exponentiation operator (“**”) in mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     newer
    -0.06
     SON
    -0.06
    -v
    -0.06
    독
    -0.06
    ucus
    -0.06
     directions
    -0.06
     Calcium
    -0.06
     �
    -0.06
    _VARIABLE
    -0.06
     VARIABLES
    -0.06
    POSITIVE LOGITS
    ',"
    0.07
    天天
    0.06
    Has
    0.06
    _scale
    0.06
     걸
    0.06
     MSE
    0.06
     должна
    0.06
    'We
    0.06
     Cristina
    0.06
    َل
    0.06
    Act Density 0.005%

    No Known Activations