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

    Neuronpedia

    INDEX
    Explanations

    configuration files

    np_max-act · gemini-2.0-flash

    This neuron responds to metadata field names or section headings (e.g. JSON/YAML keys, init‐script header tokens, Pod::Spec declarations)—i.e. labels identifying configuration or code sections.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    October
    -0.07
     طبقه
    -0.07
    !!}
    -0.06
     Newspaper
    -0.06
    abyrinth
    -0.06
    erap
    -0.06
     expecting
    -0.06
    企業
    -0.06
     CNC
    -0.06
    AppBar
    -0.06
    POSITIVE LOGITS
     imaging
    0.07
    wear
    0.06
    CEO
    0.06
     regimes
    0.06
     libido
    0.06
     impose
    0.06
    "use
    0.06
     disobed
    0.06
    スの
    0.06
    _zeros
    0.06
    Act Density 0.024%

    No Known Activations