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

    Neuronpedia

    INDEX
    Explanations

    lengthy texts

    np_max-act · gemini-2.0-flash

    The neuron activates on descriptive adjectives for electronic/techno music tracks—words like “techy,” “futuristic,” “syncopated,” “pounding,” “driving,” and “haunting.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _anim
    -0.08
    _gid
    -0.07
    _device
    -0.06
    lider
    -0.06
    时间
    -0.06
     criar
    -0.06
    gorithm
    -0.06
     predicates
    -0.06
     ，
    -0.06
    locked
    -0.06
    POSITIVE LOGITS
     diesen
    0.06
    RA
    0.06
    ік
    0.06
     amet
    0.06
    สะดวก
    0.06
    oví
    0.06
     UIAlertAction
    0.06
    补
    0.06
    iane
    0.06
    riage
    0.06
    Act Density 0.158%

    No Known Activations