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

    Neuronpedia

    INDEX
    Explanations

    writing

    np_max-act · gemini-2.0-flash

    This neuron fires on German instructional words and phrases that ask for detailed descriptions (e.g. “beschreib … detailliert” or “ausführlich Schreibstil”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    高速
    -0.06
    SAMPLE
    -0.06
    ël
    -0.06
    /cpu
    -0.06
     swept
    -0.06
     ArgumentError
    -0.06
    溫
    -0.06
     Sour
    -0.06
     filtered
    -0.06
    -part
    -0.06
    POSITIVE LOGITS
    收益
    0.07
     prose
    0.07
     kaç
    0.07
    동안
    0.07
    SETTING
    0.07
     elucid
    0.07
     cười
    0.06
     ot
    0.06
    ?"↵↵
    0.06
     typography
    0.06
    Act Density 0.025%

    No Known Activations