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

    Neuronpedia

    INDEX
    Explanations

    medicine, science

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on longer, multi-syllable content words (technical or specialized nouns and terms).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     included
    -0.07
     valor
    -0.07
    ekli
    -0.06
    %.
    -0.06
    okoj
    -0.06
    teki
    -0.06
    Phil
    -0.06
    Checkpoint
    -0.06
    ８
    -0.06
    τί
    -0.06
    POSITIVE LOGITS
    ωση
    0.06
    اورزی
    0.06
    QueryBuilder
    0.06
     rehearsal
    0.06
    activated
    0.06
     کلاس
    0.06
    _PASSWORD
    0.06
    mmc
    0.06
    ileged
    0.06
    ******
    0.06
    Act Density 0.188%

    No Known Activations