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

    Neuronpedia

    INDEX
    Explanations

    code configurations

    np_max-act · gemini-2.0-flash

    The neuron activates on quoted string literals (text enclosed in quotes) in configuration or code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ecc
    -0.07
     Одна
    -0.06
    347
    -0.06
     Proceedings
    -0.06
     bracelets
    -0.06
    avn
    -0.06
    acebook
    -0.06
    /at
    -0.06
     Hudson
    -0.06
     renting
    -0.06
    POSITIVE LOGITS
    .writeln
    0.08
    headline
    0.07
     columnName
    0.07
     onze
    0.07
    .Getter
    0.07
    (Model
    0.06
     subsidiaries
    0.06
     mods
    0.06
    .params
    0.06
     ██
    0.06
    Act Density 0.431%

    No Known Activations