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

    Neuronpedia

    INDEX
    Explanations

    ---

    np_max-act · gemini-2.0-flash

    The neuron detects the diff “original file” header marker lines that begin with three hyphens (“---”) in a unified diff.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     горм
    -0.07
    었다
    -0.06
    /cloud
    -0.06
    .Types
    -0.06
    seven
    -0.06
    (scores
    -0.06
    (Collectors
    -0.06
    <unsigned
    -0.06
    .activ
    -0.06
    .up
    -0.06
    POSITIVE LOGITS
     --
    0.10
     ---
    0.08
    --
    0.07
     الجه
    0.07
     Twitter
    0.07
    ---
    0.06
     Dob
    0.06
     antid
    0.06
     Perform
    0.06
     ----
    0.06
    Act Density 0.000%

    No Known Activations