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

    Neuronpedia

    INDEX
    Explanations

    adverbs

    np_max-act · gemini-2.0-flash

    The neuron consistently fires on numeric tokens—especially those representing decimal‐point values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .en
    -0.06
     wit
    -0.06
    σαν
    -0.06
     Canvas
    -0.06
     služeb
    -0.06
    什
    -0.06
     ferm
    -0.06
    (proc
    -0.06
     manifests
    -0.06
    /animate
    -0.06
    POSITIVE LOGITS
    ('__
    0.06
    ook
    0.06
     sacks
    0.06
     tales
    0.06
    :↵↵
    0.06
     Hook
    0.06
    Remove
    0.06
     skyline
    0.06
    _reports
    0.06
    Crow
    0.06
    Act Density 0.028%

    No Known Activations