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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     모두
    0.75
     Each
    0.72
    Each
    0.67
    すべて
    0.67
     Various
    0.64
    全て
    0.64
     Certain
    0.63
    บาง
    0.61
     Some
    0.60
     Both
    0.59
    POSITIVE LOGITS
     sorts
    1.23
     kinds
    1.17
    uding
    1.10
    usions
    1.08
    igators
    1.07
    iteration
    1.05
    ergic
    1.02
    udes
    1.00
    ude
    0.93
    usive
    0.92
    Act Density 0.092%

    No Known Activations