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

    Neuronpedia

    INDEX
    Explanations

    links to papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     그래도
    0.43
     ISBN
    0.42
    츨
    0.42
    不错的
    0.40
    蜕
    0.39
     +\
    0.38
     ఛ
    0.38
     testAvg
    0.38
     ttk
    0.37
     特に
    0.37
    POSITIVE LOGITS
     revolved
    0.40
     stoned
    0.39
    uhl
    0.39
    रिया
    0.38
     rapper
    0.38
    elo
    0.37
     sang
    0.37
    aiser
    0.37
     exceptionnelle
    0.37
     pers
    0.37
    Act Density 0.000%

    No Known Activations