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

    Neuronpedia

    INDEX
    Explanations

    code blocks for programming languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вары
    0.50
    ו
    0.46
    над
    0.42
     கண்
    0.41
    פע
    0.41
    PADDING
    0.41
    নেট
    0.40
    যার
    0.40
     கைய
    0.40
     ベース
    0.39
    POSITIVE LOGITS
    beams
    0.39
     idha
    0.38
    hoff
    0.38
     baat
    0.38
    どころ
    0.38
     recibe
    0.37
     neemt
    0.37
    rossover
    0.37
    ureen
    0.37
    letak
    0.36
    Act Density 0.010%

    No Known Activations