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

    Neuronpedia

    INDEX
    Explanations

    defining scope and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     נו
    0.50
    𒅀
    0.49
     ז
    0.46
     ס
    0.45
    󰡕
    0.45
    achtet
    0.44
     وإن
    0.44
     ב
    0.44
     कवाय
    0.44
    answers
    0.43
    POSITIVE LOGITS
     permettant
    0.46
     dekor
    0.42
    er
    0.42
     espèces
    0.41
    o
    0.41
     species
    0.41
     perimeter
    0.40
     Scope
    0.40
     Decorative
    0.40
     ensuring
    0.39
    Act Density 0.004%

    No Known Activations