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

    Neuronpedia

    INDEX
    Explanations

    incorrectly

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aufnahme
    -0.08
     కు
    -0.08
     આ
    -0.07
     ostens
    -0.07
    是不
    -0.07
    urez
    -0.07
    .design
    -0.07
     sincerely
    -0.07
     unquestionably
    -0.07
     housed
    -0.07
    POSITIVE LOGITS
    。例如
    0.09
     yaitu
    0.08
     pula
    0.08
    。有
    0.08
    。如果
    0.08
    -benar
    0.08
     sandwich
    0.08
     thành
    0.08
    ，没有
    0.08
    iales
    0.08
    Act Density 0.009%

    No Known Activations