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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to statistics or measurements

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

    Numbers within parentheses

    np_acts-logits-general · gemini-2.0-flash

    numerical statistics in mixed languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cemment
    -0.57
     works
    -0.52
    prits
    -0.52
    stdarg
    -0.51
    works
    -0.49
     Elisa
    -0.48
    abab
    -0.47
     authorities
    -0.47
     parl
    -0.47
     Pens
    -0.47
    POSITIVE LOGITS
    utilisons
    0.78
     himo
    0.65
    참고
    0.64
    Παραπομπές
    0.56
    URLConnection
    0.55
    ValueStyle
    0.54
     Questions
    0.54
     препратки
    0.53
     fawn
    0.52
    Questions
    0.52
    Act Density 0.236%

    No Known Activations