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

    Neuronpedia

    INDEX
    Explanations

    references to measurements and numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Timeframes or date ranges

    np_acts-logits-general · gemini-2.0-flash

    time intervals until or to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.62
     تضيفلها
    -0.56
    UnusedPrivate
    -0.50
     defaultstate
    -0.50
    ագրություններ
    -0.49
    },[
    -0.48
    PyExc
    -0.48
    +#+
    -0.46
    новниш
    -0.46
    ajur
    -0.45
    POSITIVE LOGITS
     till
    0.98
     until
    0.96
     hingga
    0.90
    부터
    0.90
     hanggang
    0.87
     jusqu
    0.87
     până
    0.86
     hasta
    0.86
     ועד
    0.85
     Until
    0.84
    Act Density 0.758%

    No Known Activations