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

    Neuronpedia

    INDEX
    Explanations

    GPU computation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Böl
    0.38
    eways
    0.36
     unusually
    0.34
     Hause
    0.34
     unfinished
    0.33
    ㏄
    0.33
    早い
    0.32
     νέα
    0.32
     deliberately
    0.31
     Dass
    0.31
    POSITIVE LOGITS
    JSX
    0.43
     denen
    0.39
     serait
    0.39
    Jest
    0.39
    itivo
    0.38
     JSX
    0.38
     jakie
    0.37
     doce
    0.37
    uffy
    0.37
     plais
    0.37
    Act Density 0.036%

    No Known Activations