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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relationships in mathematical contexts

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

    Mathematical expressions with numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mete
    -0.72
    Życiorys
    -0.68
    IMA
    -0.67
    áj
    -0.66
     Martine
    -0.66
     Pingback
    -0.66
     Mejía
    -0.65
    hésite
    -0.64
     Gallagher
    -0.62
     Kono
    -0.62
    POSITIVE LOGITS
     виправивши
    0.91
     فريبيس
    0.80
    ittar
    0.70
    олові
    0.62
    Accessors
    0.61
    сылкі
    0.59
     Encore
    0.57
     Nark
    0.57
     مرئيه
    0.57
    litch
    0.56
    Act Density 0.972%

    No Known Activations