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

    Neuronpedia

    INDEX
    Explanations

    specialized notation or symbols used in mathematical or scientific contexts

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

    Mathematical notation/formulae

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and archaic spelling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.92
     #
    -0.67
     Lo
    -0.64
     "
    -0.64
     T
    -0.63
     C
    -0.63
     V
    -0.62
     ...
    -0.62
     L
    -0.61
     –
    -0.61
    POSITIVE LOGITS
     myſelf
    1.33
     itſelf
    1.28
     Monfieur
    1.24
     himſelf
    1.23
     Theſe
    1.19
     uſed
    1.19
     themſelves
    1.11
     ſeveral
    1.11
     Anſ
    1.10
     deſt
    1.10
    Act Density 0.420%

    No Known Activations