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

    Neuronpedia

    INDEX
    Explanations

    is or will followed by a description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quando
    0.33
     정말
    0.30
     از
    0.29
     mío
    0.28
     kabhi
    0.28
     från
    0.28
     langage
    0.28
     من
    0.28
    يل
    0.28
     dari
    0.27
    POSITIVE LOGITS
    {\
    0.29
     također
    0.29
    arendon
    0.29
    eau
    0.28
     देखील
    0.28
    .\
    0.28
    十分
    0.28
     ebenfalls
    0.28
    収集
    0.27
     également
    0.27
    Act Density 0.177%

    No Known Activations