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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific variables and outputs in code snippets

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

    array indexing for string or array lengths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -0.59
     يتيمه
    -0.58
     CanadaChoose
    -0.54
    ValueStyle
    -0.52
    angliski
    -0.51
    SharedCtor
    -0.48
    AddWithValue
    -0.48
    ьаж
    -0.48
    Зноскі
    -0.48
     puentes
    -0.47
    POSITIVE LOGITS
    DockStyle
    0.43
     tiled
    0.43
    NUMX
    0.41
     Lolita
    0.41
     SSR
    0.40
     sill
    0.40
     ELF
    0.40
     SDM
    0.40
    jgl
    0.40
     Hela
    0.40
    Act Density 0.074%

    No Known Activations