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

    Neuronpedia

    INDEX
    Explanations

    walking plans, groups, and shoes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    歩
    0.57
    Walk
    0.49
     walk
    0.48
    walk
    0.46
    setWalk
    0.45
     Walk
    0.44
     നടക്കുന്ന
    0.44
    走进
    0.43
    เดิน
    0.43
     walked
    0.42
    POSITIVE LOGITS
     buried
    0.48
    buried
    0.45
     casualties
    0.44
    udd
    0.44
     obsolete
    0.44
     engagement
    0.43
     tours
    0.43
     subcutaneous
    0.42
     spleen
    0.41
    Fil
    0.40
    Act Density 0.006%

    No Known Activations