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

    Neuronpedia

    INDEX
    Explanations

    patterns of punctuation and numbers

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

    mathematical fractions and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnchorTagHelper
    -0.52
    IntoConstraints
    -0.48
     linkovi
    -0.47
     genie
    -0.45
    yntaxException
    -0.45
     الحره
    -0.44
    RenderAtEndOf
    -0.43
     cherchés
    -0.42
     Vikipedi
    -0.42
     chromos
    -0.41
    POSITIVE LOGITS
     calitate
    0.48
     moeite
    0.42
     argint
    0.41
     peindre
    0.40
     jongen
    0.38
     wikipagina
    0.37
     plezier
    0.37
    ppelin
    0.37
     mattina
    0.37
     coscienza
    0.37
    Act Density 0.250%

    No Known Activations