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

    Neuronpedia

    INDEX
    Explanations

    ask your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     profil
    0.37
     kombin
    0.34
    🇹
    0.34
     bukan
    0.34
     stylesheets
    0.33
     CaO
    0.33
     klin
    0.33
     bijective
    0.33
     ansatz
    0.33
     reprezent
    0.32
    POSITIVE LOGITS
    ߋ
    0.35
    నం
    0.34
    Esp
    0.32
     Πε
    0.32
    烧
    0.32
    اسة
    0.31
    European
    0.30
    ﾇ
    0.30
     سے
    0.29
     your
    0.29
    Act Density 0.002%

    No Known Activations