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

    Neuronpedia

    INDEX
    Explanations

    ate

    np_max-act · gemini-2.0-flash

    This neuron detects tokens related to character set and collation specifications (e.g., utf8mb4, COLLATE) in SQL schema definitions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ляти
    -0.06
     K
    -0.06
     olsun
    -0.06
    online
    -0.06
     episode
    -0.06
    ‌اش
    -0.06
    Ny
    -0.06
    .cast
    -0.06
    ">&
    -0.05
    .directory
    -0.05
    POSITIVE LOGITS
    came
    0.07
     {}\
    0.07
     """.
    0.06
    ++)
↵
    0.06
    -defined
    0.06
     losses
    0.06
     \''
    0.06
     {};
↵
    0.06
     screenSize
    0.06
    ="$(
    0.06
    Act Density 0.002%

    No Known Activations