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

    Neuronpedia

    INDEX
    Explanations

    list items and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Parrocchia
    0.50
    fireFlower
    0.42
    🏤
    0.42
    Gosudarstvennyj
    0.41
    Ornament
    0.40
    ंबर्स
    0.39
    avasena
    0.38
    Điều
    0.38
     صہیونیوں
    0.38
    觎
    0.38
    POSITIVE LOGITS
    0.66
    ↵
    0.49
     S
    0.46
     N
    0.45
     F
    0.44
     G
    0.43
     the
    0.42
     $
    0.40
     \
    0.40
     C
    0.40
    Act Density 0.246%

    No Known Activations