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

    Neuronpedia

    INDEX
    Explanations

    scientific papers

    np_max-act · gemini-2.0-flash

    This neuron fires on author surnames (proper names) in the paper metadata.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _alert
    -0.06
     Bert
    -0.06
    arrival
    -0.06
    figures
    -0.06
    .strings
    -0.06
     fuse
    -0.06
    ویزی
    -0.06
    $sub
    -0.06
     isLoggedIn
    -0.06
     �
    -0.05
    POSITIVE LOGITS
     ende
    0.07
    ija
    0.07
    NONE
    0.07
    .defineProperty
    0.07
     gerade
    0.07
     smirk
    0.07
     scattered
    0.07
     gradually
    0.06
    익
    0.06
    exc
    0.06
    Act Density 0.020%

    No Known Activations