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

    Neuronpedia

    INDEX
    Explanations

    specific continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    است
    0.47
    开放
    0.45
    velopper
    0.44
     الاشكال
    0.44
    ი
    0.44
    wür
    0.44
    버
    0.43
    тить
    0.43
    جب
    0.42
    Три
    0.42
    POSITIVE LOGITS
     dike
    0.54
     months
    0.52
     were
    0.46
     others
    0.46
     leader
    0.46
     সমাধি
    0.46
     $
    0.46
     "\
    0.46
     hav
    0.46
     battle
    0.46
    Act Density 0.005%

    No Known Activations