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

    Neuronpedia

    INDEX
    Explanations

    theorem proving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     theorem
    0.59
    定理
    0.53
     lemma
    0.49
     Theorem
    0.48
     theory
    0.46
     proof
    0.45
     theorems
    0.44
     тео
    0.44
     write
    0.42
     Theo
    0.42
    POSITIVE LOGITS
    Style
    0.42
    Compressed
    0.42
    Preprocessing
    0.41
    >-->
    0.40
    Deterministic
    0.40
    currentIndex
    0.39
    StackTrace
    0.38
    ტიკ
    0.37
     스타일
    0.37
    GOING
    0.37
    Act Density 0.000%

    No Known Activations