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

    Neuronpedia

    INDEX
    Explanations

    er

    np_max-act · gemini-2.0-flash

    The neuron fires on URL components—especially domain names and path segments (e.g. “gnome,” “gstreamer,” “org,” etc.)—indicating it detects links and their constituent tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ενώ
    -0.07
    (KeyCode
    -0.06
    ScrollIndicator
    -0.06
     프로
    -0.06
     �
    -0.06
    λί
    -0.06
    학년도
    -0.06
    uální
    -0.06
     kao
    -0.06
     Kin
    -0.06
    POSITIVE LOGITS
    removeClass
    0.07
    먹
    0.07
     great
    0.06
    429
    0.06
     Towards
    0.06
     QtCore
    0.06
     ISSN
    0.06
    avings
    0.06
    apur
    0.06
     Usuarios
    0.06
    Act Density 0.077%

    No Known Activations