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

    Neuronpedia

    INDEX
    Explanations

    Code syntax

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literal tokens (especially decimal‐point numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sequences
    -0.07
     evident
    -0.06
    .light
    -0.06
    _gain
    -0.06
    cker
    -0.06
     quarters
    -0.06
    lined
    -0.05
    terr
    -0.05
    obb
    -0.05
    bolt
    -0.05
    POSITIVE LOGITS
     شهید
    0.07
     paced
    0.06
     أخ
    0.06
     člověk
    0.06
     еж
    0.06
    ,cv
    0.06
    การเล
    0.06
     sécur
    0.06
     профилакти
    0.06
     Ist
    0.06
    Act Density 0.036%

    No Known Activations