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

    Neuronpedia

    INDEX
    Explanations

    higher speeds, no logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    0.54
    О
    0.54
    ை
    0.52
    П
    0.52
    я
    0.50
    В
    0.49
    ей
    0.48
    ста
    0.47
    и
    0.46
    व
    0.46
    POSITIVE LOGITS
     contiguous
    0.52
     positifs
    0.52
     Hence
    0.50
     digraph
    0.50
     fleks
    0.50
     parameter
    0.50
     url
    0.50
     eraser
    0.50
     skapa
    0.50
     script
    0.49
    Act Density 0.003%

    No Known Activations