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

    Neuronpedia

    INDEX
    Explanations

    names and ship designations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ༀ
    -3.94
    ︲
    -3.44
    뀨
    -3.31
    臯
    -3.25
    ه
    -3.16
    0
    -3.16
    尛
    -3.05
    м
    -3.00
    聼
    -2.92
    躂
    -2.92
    POSITIVE LOGITS
    2.88
    2.77
    缎
    2.56
    ៚
    2.41
    ’，
    2.41
    各种
    2.34
     privadas
    2.34
    ₿
    2.25
    ’?
    2.25
    ”—
    2.25
    Act Density 0.011%

    No Known Activations