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

    Neuronpedia

    INDEX
    Explanations

    variables and integer declarations in programming code

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

    Appears before loop variables or indices

    np_acts-logits-general · gemini-2.0-flash

    loop initialization using i or x

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.99
    évaluateur
    -0.98
    MigrationBuilder
    -0.90
    IsContent
    -0.90
    OCCURRED
    -0.77
     Administrativna
    -0.75
    tonsoft
    -0.74
    Geplaatst
    -0.70
     initComponents
    -0.69
     ujednoznacz
    -0.69
    POSITIVE LOGITS
     =
    0.68
    =
    0.61
     counter
    0.54
     :
    0.53
    loop
    0.51
     Counter
    0.48
    counter
    0.48
    Counter
    0.47
    ;;)
    0.47
     Loop
    0.46
    Act Density 0.080%

    No Known Activations