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

    Neuronpedia

    INDEX
    Explanations

    code blocks and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ferr
    0.47
    ゞ
    0.46
    ният
    0.45
     vergangenen
    0.45
     basta
    0.44
    ρός
    0.43
    ()-
    0.42
     skate
    0.42
     belliger
    0.42
     BEACH
    0.41
    POSITIVE LOGITS
    መሪያ
    0.47
    𝙡
    0.42
    ли
    0.42
     minValue
    0.41
    го
    0.40
    코드
    0.40
    wertung
    0.40
     illetve
    0.39
    造型
    0.39
    칼
    0.39
    Act Density 0.001%

    No Known Activations