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

    Neuronpedia

    INDEX
    Explanations

    reporting

    np_max-act · gemini-2.0-flash

    This neuron lights up on mid-frequency, multi-syllabic words typical of formal scientific or technical writing (e.g., validated, strategies, data).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ázky
    -0.07
     Greenwich
    -0.06
    vasion
    -0.06
    notin
    -0.06
     congen
    -0.06
     supra
    -0.06
    番号
    -0.06
     hra
    -0.06
     жизнь
    -0.06
     Raises
    -0.06
    POSITIVE LOGITS
    [parent
    0.06
    .radians
    0.06
     Dinner
    0.06
    -pt
    0.06
    Less
    0.06
    ìm
    0.06
     días
    0.06
    Allowed
    0.06
     �
    0.06
     imz
    0.06
    Act Density 0.379%

    No Known Activations