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

    Neuronpedia

    INDEX
    Explanations

    ://

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—especially floating‐point or version‐style numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     COPYING
    -0.07
    _SERVICE
    -0.06
    ’app
    -0.06
     ",
↵
    -0.06
    'app
    -0.06
     McK
    -0.06
    burgh
    -0.06
    WordPress
    -0.06
    má
    -0.06
    达到
    -0.06
    POSITIVE LOGITS
    تور
    0.07
     Detected
    0.07
     erv
    0.06
     February
    0.06
     sito
    0.06
     obnov
    0.06
    pty
    0.06
     何
    0.06
     October
    0.06
    }\
    0.06
    Act Density 0.018%

    No Known Activations