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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens in first‐person posts where the author describes or points to their own code/tool (e.g. “I wrote…”, “solution”, repo URLs).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ो
    -0.07
    opez
    -0.06
     PRINT
    -0.06
    ensaje
    -0.06
    _OPTS
    -0.06
     Dodgers
    -0.06
     Siege
    -0.06
     zám
    -0.06
    Neill
    -0.06
    .Consumer
    -0.06
    POSITIVE LOGITS
    한
    0.07
     evenly
    0.06
    slice
    0.06
     ainsi
    0.06
    stellen
    0.06
    _invalid
    0.06
     acum
    0.06
    imestone
    0.06
    alarında
    0.06
    ujeme
    0.06
    Act Density 0.048%

    No Known Activations