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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols related to vector spaces and isomorphisms

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

    Mathematical notation

    np_acts-logits-general · gemini-2.0-flash

    mathematical vector spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pengh
    -0.52
     CGPoint
    -0.47
    writerow
    -0.43
    muo
    -0.42
    setopt
    -0.41
    kuš
    -0.41
    ويت
    -0.41
    Dominique
    -0.40
    gorod
    -0.40
    istoitu
    -0.40
    POSITIVE LOGITS
     Италијани
    0.73
     otomatig
    0.71
     sheet
    0.69
    sheet
    0.68
    <?
    0.66
     Sheet
    0.66
    SHEET
    0.65
     sheets
    0.63
     tongues
    0.61
    windowFixed
    0.61
    Act Density 0.299%

    No Known Activations