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

    Neuronpedia

    INDEX
    Explanations

    by followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >∕
    0.46
     టిప్పు
    0.44
    ならラクマ
    0.43
    ActionsForRule
    0.43
    糺
    0.42
     stockno
    0.42
    🧬
    0.42
    INDUSTRIAL
    0.41
     હત્યા
    0.41
    Collide
    0.41
    POSITIVE LOGITS
     Zhang
    0.81
     Huang
    0.76
     Wang
    0.73
     Liu
    0.71
    Zhang
    0.71
     Zhou
    0.71
     van
    0.70
     Zhao
    0.70
     Gao
    0.70
     Wu
    0.68
    Act Density 0.007%

    No Known Activations