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

    Neuronpedia

    INDEX
    Explanations

    lists or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    न्यास
    0.41
     Cake
    0.40
    恒
    0.39
    Cake
    0.39
    ＂
    0.38
    Kell
    0.37
    ₆
    0.37
    恆
    0.36
    ashion
    0.36
     केक
    0.35
    POSITIVE LOGITS
    ូច
    0.39
    เหมาะ
    0.39
     './
    0.38
     imdb
    0.37
     गुर्जर
    0.36
     donated
    0.36
    iml
    0.35
     rencontr
    0.35
     நடித்த
    0.34
     loadAnimation
    0.34
    Act Density 0.000%

    No Known Activations