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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and structural elements

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

    occurrences of LaTeX or mathematical notation indicators

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

    Also let

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     −
    -0.54
    дер
    -0.52
    ens
    -0.51
    ppan
    -0.50
    isi
    -0.50
     Ant
    -0.50
     (
    -0.50
     +
    -0.49
    itten
    -0.48
     ro
    -0.48
    POSITIVE LOGITS
     myſelf
    1.07
     Theſe
    0.99
     Audiodateien
    0.94
     ſeveral
    0.93
     himſelf
    0.91
    +#+#
    0.89
     itſelf
    0.89
     themſelves
    0.87
     fometimes
    0.87
     whoſe
    0.86
    Act Density 0.011%

    No Known Activations