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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash

    The neuron activates on programming‐style identifiers and constant names (e.g. class names, macros, module or library identifiers) within source code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    icon
    -0.08
    _Options
    -0.07
    캐
    -0.07
     language
    -0.07
    _week
    -0.06
    .offsetWidth
    -0.06
     antidepress
    -0.06
     essentially
    -0.06
     man
    -0.06
    .Keyboard
    -0.06
    POSITIVE LOGITS
    EndElement
    0.06
    _minor
    0.06
     тобто
    0.06
    pectives
    0.06
    [list
    0.06
    联盟
    0.06
    _DT
    0.06
    readonly
    0.06
    ระเบ
    0.06
     fv
    0.06
    Act Density 0.089%

    No Known Activations