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

    Neuronpedia

    INDEX
    Explanations

    O words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ጠቃ
    0.38
    硯
    0.36
     diagonalizable
    0.36
     Ичиго
    0.36
    графия
    0.36
    ल्लभ
    0.36
    ާ
    0.35
    سطس
    0.35
    msford
    0.35
    uzioni
    0.34
    POSITIVE LOGITS
     O
    4.47
    O
    3.27
     ओ
    3.16
     О
    2.94
     o
    2.53
     Ο
    2.50
     โอ
    2.34
    𝑂
    2.33
    Ｏ
    2.19
     Oo
    2.11
    Act Density 0.181%

    No Known Activations