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

    Neuronpedia

    INDEX
    Explanations

    code definitions and implementations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    made
    0.74
    en
    0.68
    gene
    0.68
    एशन
    0.67
    gan
    0.66
    lim
    0.66
    ighters
    0.65
    Plan
    0.65
    cum
    0.64
    sax
    0.64
    POSITIVE LOGITS
     Defining
    0.75
     SKSpriteNode
    0.74
     Implementation
    0.72
     predeceased
    0.69
     определяется
    0.69
    ორი
    0.68
     ці
    0.68
    ülő
    0.68
     участке
    0.67
    āta
    0.67
    Act Density 0.052%

    No Known Activations