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

    Neuronpedia

    INDEX
    Explanations

    numbers or x

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens containing digit sequences (e.g. hardware or driver model numbers) in source code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    components related to audio driver specifications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _fid
    -0.06
     vrij
    -0.06
    -Sep
    -0.06
    _cred
    -0.06
    .Go
    -0.06
     Kron
    -0.06
     Wallpaper
    -0.06
     Serializable
    -0.06
     Druid
    -0.06
     ziyaret
    -0.06
    POSITIVE LOGITS
     спів
    0.07
     award
    0.07
    Model
    0.07
    thus
    0.07
    型
    0.07
     problem
    0.07
     Bez
    0.06
     politic
    0.06
     processing
    0.06
    .widget
    0.06
    Act Density 0.024%

    No Known Activations