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

    Neuronpedia

    INDEX
    Explanations

    consecutive tournament wins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    させた
    0.47
    していた
    0.47
    Opel
    0.44
    してる
    0.43
    ቮ
    0.42
    Have
    0.41
    चुनाव
    0.40
    起動
    0.39
    信仰
    0.39
    就在
    0.39
    POSITIVE LOGITS
     \"
    0.40
     March
    0.40
     '@
    0.39
     removing
    0.39
     Deb
    0.39
     '.
    0.39
    ROff
    0.39
     freeing
    0.39
     '
    0.38
     sodium
    0.38
    Act Density 0.000%

    No Known Activations