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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash

    The neuron activates on user‐directed calls to action or instructional phrases (e.g. “you can download…,” “find out our other pictures…,” “click the image…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _dice
    -0.07
    اته
    -0.06
    movies
    -0.06
     wel
    -0.06
     Conditions
    -0.06
    는
    -0.06
    -turned
    -0.06
    ратег
    -0.06
    giatan
    -0.06
     servisi
    -0.06
    POSITIVE LOGITS
    ezier
    0.07
    _SECURITY
    0.07
     runes
    0.06
    enny
    0.06
     vý
    0.06
    .sparse
    0.06
     Badge
    0.06
    .DOWN
    0.06
     towering
    0.06
    gameObject
    0.06
    Act Density 0.007%

    No Known Activations