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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ע
    0.53
     特に
    0.52
    ることが
    0.50
    וד
    0.49
    იკ
    0.49
     בא
    0.46
     Caedwalla
    0.46
     명
    0.45
     ด่า
    0.45
     особливо
    0.44
    POSITIVE LOGITS
     comforts
    0.48
     engagements
    0.43
     consoles
    0.42
    riev
    0.42
     teammates
    0.41
    me
    0.40
     workouts
    0.40
    ({
    0.40
     autocratic
    0.40
    re
    0.40
    Act Density 0.005%

    No Known Activations