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

    Neuronpedia

    INDEX
    Explanations

    svg markup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     женой
    0.30
    楔
    0.30
    Mâc
    0.29
    𒂍
    0.29
    <unused711>
    0.28
    alaikumsalam
    0.28
    莞
    0.28
    }}}^{
    0.27
    ocese
    0.27
     церков
    0.27
    POSITIVE LOGITS
     display
    0.34
     Display
    0.33
     <
    0.32
    display
    0.32
    "><
    0.31
    Display
    0.30
    ">
    0.30
     displaystyle
    0.30
     Param
    0.29
     param
    0.29
    Act Density 0.000%

    No Known Activations