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

    Neuronpedia

    INDEX
    Explanations

    Song lyrics

    np_max-act · gemini-2.0-flash

    The neuron fires on song‐writing structural cues—e.g. the word “song” itself and section labels like “Verse,” “Chorus,” etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     obj
    -0.07
    OG
    -0.07
    (cls
    -0.06
    ography
    -0.06
     Legislature
    -0.06
     skating
    -0.06
    機
    -0.06
     poop
    -0.06
    _renderer
    -0.06
     climbed
    -0.06
    POSITIVE LOGITS
     cosplay
    0.07
    /order
    0.07
     trata
    0.06
    .inv
    0.06
    .TRUE
    0.06
    Drink
    0.06
    )reader
    0.06
     μεγ
    0.06
    agrant
    0.06
     abrasive
    0.06
    Act Density 0.018%

    No Known Activations