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

    Neuronpedia

    INDEX
    Explanations

    civil wars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ことで
    1.42
    ب
    1.37
    äischen
    1.34
    ките
    1.33
    こちらの
    1.23
    andı
    1.23
    ємо
    1.22
    ੁ
    1.22
    分別
    1.21
    いずれ
    1.20
    POSITIVE LOGITS
     multitudes
    1.27
    7
    1.12
    5
    1.11
     an
    1.10
     floods
    1.10
    9
    1.09
    8
    1.09
     blew
    1.07
    ო
    1.07
    advant
    1.06
    Act Density 0.000%

    No Known Activations