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

    Neuronpedia

    INDEX
    Explanations

    references to statistical comparisons or summary data

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

    Stack Overflow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.59
     houſe
    -0.57
     disambiguazione
    -0.56
     cession
    -0.55
     Houſe
    -0.55
     purpoſe
    -0.54
     fubject
    -0.53
     ſche
    -0.53
     pleaſure
    -0.52
    aarrggbb
    -0.51
    POSITIVE LOGITS
     Ter
    0.58
     ter
    0.56
    Ter
    0.56
     terper
    0.52
     נ
    0.46
     최
    0.44
     meest
    0.44
     Terrell
    0.42
     самая
    0.42
     contained
    0.41
    Act Density 0.003%

    No Known Activations