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

    Neuronpedia

    INDEX
    Explanations

    circumference

    np_max-act · gemini-2.0-flash

    The neuron specifically detects occurrences of the word “circumference.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Golden
    -0.07
     Hay
    -0.07
     shaded
    -0.06
    _loading
    -0.06
     Codable
    -0.06
     asia
    -0.06
    Default
    -0.06
    366
    -0.06
    Elizabeth
    -0.06
    518
    -0.06
    POSITIVE LOGITS
     doprav
    0.07
     lurking
    0.07
     circumference
    0.07
     CCC
    0.07
     Lik
    0.06
    (Call
    0.06
     лиц
    0.06
    (docs
    0.06
    ��
    0.06
     lớ
    0.06
    Act Density 0.004%

    No Known Activations