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

    Neuronpedia

    INDEX
    Explanations

    log

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of logarithmic transformations or log‐scaled data (e.g. “log,” “transform(ed),” “transformation”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     uu
    -0.07
    thed
    -0.06
    'B
    -0.06
    tera
    -0.06
    few
    -0.06
     Leban
    -0.06
    UL
    -0.06
     Osman
    -0.06
    pson
    -0.06
    xa
    -0.06
    POSITIVE LOGITS
     окруж
    0.07
     χρόνια
    0.07
    ological
    0.07
    σματα
    0.06
    odář
    0.06
    .parts
    0.06
     setMessage
    0.06
     Session
    0.06
     فاصله
    0.06
     Douglas
    0.06
    Act Density 0.004%

    No Known Activations