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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of file system paths, file or folder names, and other code‐style identifiers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     vn
    -0.06
    @dynamic
    -0.06
    _bn
    -0.06
    ляет
    -0.06
     GV
    -0.06
     signaled
    -0.06
    Rol
    -0.06
     summarized
    -0.06
    ystems
    -0.06
     Connection
    -0.06
    POSITIVE LOGITS
    [mid
    0.07
    	progress
    0.06
     SAVE
    0.06
    0.06
     cites
    0.06
     train
    0.06
     γε
    0.06
    ‫
    0.06
     WebView
    0.06
     �
    0.06
    Act Density 0.658%

    No Known Activations