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

    Neuronpedia

    INDEX
    Explanations

    all / everything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vao
    0.43
    stm
    0.39
    Mats
    0.37
     মুজিবকে
    0.37
    mau
    0.37
    STM
    0.36
    Adresse
    0.36
    Address
    0.35
    beiten
    0.35
    vadipine
    0.35
    POSITIVE LOGITS
    盯
    0.45
    的一切
    0.41
     kolejne
    0.39
     increasingly
    0.39
     ხელისუფ
    0.39
     известные
    0.39
     Increasingly
    0.38
     mögliche
    0.38
     स्टार्टिंग
    0.38
     Else
    0.38
    Act Density 0.006%

    No Known Activations