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

    Neuronpedia

    INDEX
    Explanations

    code and version numbers

    np_max-act · gemini-2.0-flash

    This neuron detects version‐number tokens (digits and separators like dots, hyphens, and qualifiers) in configuration and code files.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _ONE
    -0.06
     MCC
    -0.06
     phận
    -0.06
     eighteen
    -0.06
    ectors
    -0.06
     grows
    -0.05
    _DOWN
    -0.05
    ographer
    -0.05
    oscope
    -0.05
     MA
    -0.05
    POSITIVE LOGITS
    unused
    0.07
    scriptions
    0.07
    xbf
    0.07
     」
    0.07
     Олександ
    0.06
    Players
    0.06
    (None
    0.06
    .timestamps
    0.06
     Lik
    0.06
    廣
    0.06
    Act Density 0.007%

    No Known Activations