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

    Neuronpedia

    INDEX
    Explanations

    loops and ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     방법을
    0.82
     văn
    0.74
     방법
    0.73
     couch
    0.69
     documentary
    0.68
     panoramic
    0.68
     LIM
    0.65
    注意事項
    0.64
     Crowd
    0.64
     prose
    0.63
    POSITIVE LOGITS
    Math
    0.93
    Integer
    0.79
    lfloor
    0.75
    Arithmetic
    0.75
    Easing
    0.74
    usize
    0.73
    parseInt
    0.72
     i
    0.71
    Debugger
    0.71
     Mathf
    0.71
    Act Density 0.363%

    No Known Activations