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

    Neuronpedia

    INDEX
    Explanations

    HTML/code endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    学習
    0.38
     lifelong
    0.35
    鬪
    0.34
     Lernen
    0.34
     लर्न
    0.33
     کھانا
    0.32
    𒄀
    0.32
    Learning
    0.32
     పెరుగు
    0.32
    的学习
    0.32
    POSITIVE LOGITS
    .}
    0.39
    }.
    0.35
    end
    0.34
    }
    0.33
     }//
    0.32
    ord
    0.32
    \}.
    0.31
    .
    0.31
    ti
    0.30
    tt
    0.30
    Act Density 0.019%

    No Known Activations