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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols often used in advanced mathematical notation

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

    mathematical symbols and relations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.93
     betweenstory
    -0.86
     AssemblyCompany
    -0.86
     Geiſt
    -0.85
     ſche
    -0.85
    adaptiveStyles
    -0.81
     esternos
    -0.80
     indígen
    -0.79
     ſever
    -0.78
     houſe
    -0.78
    POSITIVE LOGITS
     \
    0.75
     is
    0.52
     be
    0.50
    s
    0.50
    \
    0.49
    self
    0.48
     has
    0.48
     can
    0.48
     self
    0.47
     s
    0.45
    Act Density 0.390%

    No Known Activations