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

    Neuronpedia

    INDEX
    Explanations

    code structure and markup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    স্বর
    0.35
    iscid
    0.35
    柠
    0.35
    තුර
    0.34
    utenant
    0.34
    akuan
    0.34
    τού
    0.34
    鸦
    0.33
    တော်
    0.33
    করি
    0.33
    POSITIVE LOGITS
    ഘ
    0.41
    lc
    0.39
     arrond
    0.39
    eson
    0.38
    ],
    0.38
    4
    0.38
    1
    0.37
    \%),
    0.37
    L
    0.37
     Arrangement
    0.36
    Act Density 0.000%

    No Known Activations