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

    Neuronpedia

    INDEX
    Explanations

    errands and purchase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    monton
    0.38
    Tweet
    0.38
    鎧
    0.37
    bü
    0.37
    ныя
    0.36
     mouve
    0.36
    ιν
    0.36
    輒
    0.36
    ęg
    0.36
    ц
    0.36
    POSITIVE LOGITS
    成立于
    0.45
     defending
    0.42
     astr
    0.39
     सर
    0.39
     Strauss
    0.37
     Sare
    0.37
     Stav
    0.36
    رمی
    0.36
     TabLayout
    0.36
     provides
    0.35
    Act Density 0.000%

    No Known Activations