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

    Neuronpedia

    INDEX
    Explanations

    Time measurements

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of time intervals and follow‐up durations (e.g. “12 months,” “6‐minute test,” “18-month follow-up”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    али
    -0.07
    ｗｗ
    -0.07
    _RT
    -0.06
    Alright
    -0.06
    inq
    -0.06
     wiki
    -0.06
    acific
    -0.06
    finally
    -0.06
     casual
    -0.06
     wounded
    -0.06
    POSITIVE LOGITS
    -sale
    0.07
    .showMessageDialog
    0.07
    retim
    0.06
    .song
    0.06
    wanted
    0.06
    izia
    0.06
     gezocht
    0.06
    KHTML
    0.06
    英国
    0.06
    ğinde
    0.06
    Act Density 0.025%

    No Known Activations