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

    Neuronpedia

    INDEX
    Explanations

    code/identifiers

    np_max-act · gemini-2.0-flash

    The neuron detects placeholder entity names of the form “NAME_〈number〉.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     troublesome
    -0.07
     metabolic
    -0.07
     soc
    -0.07
    .id
    -0.06
     UIStoryboard
    -0.06
    isory
    -0.06
    常
    -0.06
     conceivable
    -0.06
    .Requires
    -0.06
    çon
    -0.06
    POSITIVE LOGITS
     milfs
    0.07
     файла
    0.07
    _serial
    0.07
     InputDecoration
    0.06
    .Length
    0.06
    imeo
    0.06
     示例
    0.06
    ้าห
    0.06
    яви
    0.06
     eski
    0.06
    Act Density 0.043%

    No Known Activations