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

    Neuronpedia

    INDEX
    Explanations

    code-related variable declarations, data types, and operations

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

    Floating-point numbers (double, float)

    np_acts-logits-general · gemini-2.0-flash

    double, float, CGFloat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     count
    -0.57
     carried
    -0.55
     COUNT
    -0.53
     numbered
    -0.53
     counted
    -0.53
     counts
    -0.53
     Count
    -0.53
    Counting
    -0.52
     counting
    -0.52
    counting
    -0.52
    POSITIVE LOGITS
     {:.
    0.87
    :%.
    0.81
    FloatField
    0.77
     atof
    0.77
    URLException
    0.74
    kegaard
    0.74
    float
    0.72
     Float
    0.71
     FileReader
    0.69
    MotionEvent
    0.69
    Act Density 0.545%

    No Known Activations