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

    Neuronpedia

    INDEX
    Explanations

    numeric values and formatting in text

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

    Numbers indicating quantity, count, or amount

    np_acts-logits-general · gemini-2.0-flash

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </h2>
    -0.69
       
    -0.67
     −
    -0.63
     
    -0.58
    </strong>
    -0.57
     beziehungs
    -0.57
    . 
    -0.57
     –,
    -0.56
     »,
    -0.55
     ?
    -0.55
    POSITIVE LOGITS
    ValueStyle
    0.74
    maybe
    0.73
     HUGE
    0.67
     yg
    0.65
    大半
    0.63
     alot
    0.63
    alot
    0.62
    VERY
    0.61
     atleast
    0.60
     maybe
    0.59
    Act Density 0.120%

    No Known Activations