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

    Neuronpedia

    INDEX
    Explanations

    executing commands or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    во
    0.42
    も含
    0.38
    ’
    0.38
    𝔰
    0.37
     المللی
    0.36
    рт
    0.36
    кмекер
    0.36
     поводу
    0.36
     театр
    0.36
    гаа
    0.36
    POSITIVE LOGITS
     for
    0.38
    il
    0.34
     It
    0.34
    υτό
    0.34
    ↵
    0.33
    ant
    0.33
     have
    0.30
     He
    0.30
     This
    0.30
     Executes
    0.30
    Act Density 0.103%

    No Known Activations