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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron fires on CamelCase or PascalCase identifier tokens, highlighting class, interface, and other type names in source code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Lean
    -0.07
    )get
    -0.07
    warts
    -0.06
    fb
    -0.06
     wirklich
    -0.06
     Lens
    -0.06
     SW
    -0.06
     Game
    -0.06
     bug
    -0.06
    サイト
    -0.06
    POSITIVE LOGITS
    kontakte
    0.06
     earrings
    0.06
    しても
    0.06
    .CodeAnalysis
    0.06
    .ColumnStyles
    0.06
    _HEAD
    0.06
    -employed
    0.06
    .rpm
    0.06
     amd
    0.06
     anlamda
    0.06
    Act Density 0.058%

    No Known Activations