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

    Neuronpedia

    INDEX
    Explanations

    numbers and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ▛
    0.41
    亼
    0.38
    绺
    0.38
    uć
    0.37
    萋
    0.36
    洳
    0.36
    淝
    0.35
    🥜
    0.35
    茈
    0.35
     continuité
    0.35
    POSITIVE LOGITS
    9
    0.49
    6
    0.44
    5
    0.42
    4
    0.41
    8
    0.41
    2
    0.38
    7
    0.38
    0
    0.35
    1
    0.34
    3
    0.33
    Act Density 0.034%

    No Known Activations