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

    Neuronpedia

    INDEX
    Explanations

    Russian and Polish speaking context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     километ
    0.39
    ⵖ
    0.39
    AUTH
    0.39
     میلیون
    0.39
     Maß
    0.38
     عامل
    0.38
     끊
    0.38
     getView
    0.38
    ností
    0.37
     ய
    0.37
    POSITIVE LOGITS
     po
    0.54
    0.38
    套
    0.37
     по
    0.37
     CDs
    0.36
    ext
    0.36
     ext
    0.35
    Kirk
    0.35
     gr
    0.35
    edict
    0.35
    Act Density 0.001%

    No Known Activations