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

    Neuronpedia

    INDEX
    Explanations

    hovering over, options, responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    しかし
    0.75
    Ant
    0.74
    Is
    0.69
    Ad
    0.67
     masih
    0.66
     Sedangkan
    0.65
    Def
    0.64
    Car
    0.64
     valamint
    0.63
    Ass
    0.63
    POSITIVE LOGITS
     worry
    0.80
     walkable
    0.78
     refine
    0.76
    <unused2095>
    0.75
     upscale
    0.75
    ᴗ
    0.75
    sthresh
    0.75
     expend
    0.73
     incentive
    0.73
     %@",
    0.73
    Act Density 0.000%

    No Known Activations