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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash

    This neuron detects numeric values in comparative or statistical contexts (e.g. figures given for “compared,” “to,” or “lowest” in quantitative comparisons).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ยาว
    -0.07
     Roose
    -0.07
    572
    -0.06
     giorn
    -0.06
     "'";↵
    -0.06
    นอ
    -0.06
     namedtuple
    -0.06
     Atlas
    -0.06
     Researchers
    -0.06
    River
    -0.06
    POSITIVE LOGITS
    'es
    0.07
     мат
    0.07
     oficial
    0.07
     points
    0.07
    Questions
    0.06
     уровне
    0.06
    ections
    0.06
     FXMLLoader
    0.06
    (obj
    0.06
     duct
    0.06
    Act Density 0.040%

    No Known Activations