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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and error handling in programming code

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

    function calls and code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.62
     diffusion
    -0.43
     kaarangay
    -0.42
    titleMargin
    -0.42
    Walls
    -0.42
    velocityY
    -0.42
    цездатний
    -0.42
     Walls
    -0.41
     walls
    -0.41
     Presumably
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.69
    ArgumentParser
    0.59
     ***!
    0.46
     الحره
    0.45
    AndEndTag
    0.44
     nahilalakip
    0.43
    ביוגרפיה
    0.43
    ScopeManager
    0.43
     wireType
    0.42
     Audiodateien
    0.42
    Act Density 0.010%

    No Known Activations