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

    Neuronpedia

    INDEX
    Explanations

    numerical values, particularly in the context of statistical or measurement data

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

    Numbers followed by "±" or in parentheses

    np_acts-logits-general · gemini-2.0-flash

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     one
    -0.65
     micro
    -0.63
    <eos>
    -0.63
    0
    -0.61
    ,
    -0.60
     ko
    -0.60
     (
    -0.60
     no
    -0.60
     zero
    -0.58
     O
    -0.57
    POSITIVE LOGITS
    ConstraintMaker
    1.01
     Theſe
    0.90
     ſeveral
    0.89
     ſtate
    0.88
     itſelf
    0.86
     Majefty
    0.86
     pinulongan
    0.85
     whoſe
    0.85
     purpoſe
    0.84
    MLLoader
    0.84
    Act Density 0.556%

    No Known Activations