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

    Neuronpedia

    INDEX
    Explanations

    want to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     úrov
    0.56
    <unused0>
    0.53
    tFileInputExcel
    0.50
    ’;
    0.50
     أوروب
    0.48
    ([],
    0.48
    льності
    0.47
    iculaire
    0.47
    ELEASE
    0.47
    linkOpacity
    0.47
    POSITIVE LOGITS
     I
    0.58
    و
    0.50
    T
    0.50
     the
    0.49
    ک
    0.48
     Legal
    0.47
    ل
    0.45
    अ
    0.45
     of
    0.44
    com
    0.44
    Act Density 0.001%

    No Known Activations