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

    Neuronpedia

    INDEX
    Explanations

    numbers separated by commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不同
    0.39
    ير
    0.35
    ер
    0.34
     *\
    0.34
    renderCamera
    0.34
    pèce
    0.33
     हंसी
    0.33
    ær
    0.33
    +.
    0.32
    డిగా
    0.31
    POSITIVE LOGITS
    ﹑
    0.40
    ,
    0.38
    }^{+},
    0.38
     rafters
    0.37
     for
    0.36
     see
    0.36
     College
    0.35
     ranged
    0.35
     characterise
    0.35
    illation
    0.34
    Act Density 0.119%

    No Known Activations