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

    Neuronpedia

    INDEX
    Explanations

    how it's done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    くる
    0.45
     повер
    0.43
     Stanford
    0.42
     Derby
    0.42
    名
    0.42
     Burb
    0.42
    軾
    0.42
    ak
    0.41
    Is
    0.41
    に
    0.41
    POSITIVE LOGITS
     fashions
    0.46
     perceiving
    0.45
    ＾＾
    0.45
     sociable
    0.44
     mivel
    0.44
    biotics
    0.44
     soviet
    0.43
    いろんな
    0.43
     biotechn
    0.43
     cognit
    0.43
    Act Density 0.000%

    No Known Activations