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

    Neuronpedia

    INDEX
    Explanations

    sections related to inclusivity and accessibility in various contexts

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

    Tokens related to broadness or generality

    np_acts-logits-general · gemini-2.0-flash

    generality and universality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sav
    -0.38
     Dun
    -0.35
    [],
    -0.35
     rear
    -0.34
    lag
    -0.33
    Smart
    -0.33
     lead
    -0.32
     Mish
    -0.32
    Rear
    -0.32
     paper
    -0.32
    POSITIVE LOGITS
     universality
    0.86
     universal
    0.85
     universelle
    0.84
     universale
    0.84
    universal
    0.82
     nahilalakip
    0.80
     universel
    0.75
     broadest
    0.68
     widest
    0.68
    Universal
    0.66
    Act Density 0.550%

    No Known Activations