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

    Neuronpedia

    INDEX
    Explanations

    numbered lists

    np_acts-logits-general · gemini-2.5-flash-lite

    Naruto, Shippuden, Shonen Jump

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ون
    0.41
    et
    0.38
    ো
    0.36
    ップ
    0.35
    դ
    0.34
    υτό
    0.34
    鸫
    0.34
    ோருக்கு
    0.33
    ெற்ற
    0.33
    鸩
    0.33
    POSITIVE LOGITS
     is
    0.52
     an
    0.47
     was
    0.44
     in
    0.44
    0.44
    :
    0.44
     to
    0.36
     :
    0.35
    !
    0.35
     t
    0.34
    Act Density 0.003%

    No Known Activations