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

    Neuronpedia

    INDEX
    Explanations

    groups of whitespace or unspecified tokens

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

    control flow keywords, case statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.68
    ########.
    -0.59
     kasarigan
    -0.54
    httphttps
    -0.52
    desertcart
    -0.52
     poffe
    -0.51
     enfans
    -0.51
    anskje
    -0.51
    VYMaps
    -0.50
     endforeach
    -0.50
    POSITIVE LOGITS
     "..\..\..\
    0.50
     "..\..\
    0.44
     else
    0.43
    enumi
    0.40
     eventuali
    0.39
     mesmas
    0.36
    BufferException
    0.35
    ..\..\
    0.34
     plupart
    0.33
    webElement
    0.33
    Act Density 0.006%

    No Known Activations