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

    Neuronpedia

    INDEX
    Explanations

    making things easier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     เป็น
    0.44
     rnorm
    0.43
     resultados
    0.42
     breve
    0.41
     נ
    0.41
     ד
    0.41
     Poems
    0.40
     venenatis
    0.39
    侵害
    0.39
     interests
    0.39
    POSITIVE LOGITS
     Easier
    0.77
     simplifies
    0.76
    Ease
    0.76
     simplify
    0.75
     ease
    0.73
     Ease
    0.71
     easier
    0.70
    ease
    0.69
    simplify
    0.69
    Simplified
    0.67
    Act Density 0.106%

    No Known Activations