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

    Neuronpedia

    INDEX
    Explanations

    non-English characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     عندما
    0.40
     verbs
    0.37
     جمله
    0.37
     جمل
    0.32
     kulland
    0.32
    👈
    0.32
     استفاده
    0.32
     फक्त
    0.32
     مکمل
    0.31
     راحت
    0.31
    POSITIVE LOGITS
    j
    0.37
    J
    0.37
    iu
    0.35
    ui
    0.35
    {
    0.34
    on
    0.34
    ile
    0.34
    ai
    0.33
    EM
    0.33
    N
    0.33
    Act Density 0.123%

    No Known Activations