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

    Neuronpedia

    INDEX
    Explanations

    end marker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pil
    0.39
    Lavender
    0.38
    Alpha
    0.37
     आगा
    0.37
    Purg
    0.35
    Algorithm
    0.35
     bardziej
    0.35
    Params
    0.35
    olation
    0.35
     trì
    0.35
    POSITIVE LOGITS
    年后
    0.45
     Ending
    0.43
    结尾
    0.42
     vivi
    0.40
     конца
    0.38
     तैयारियां
    0.38
    结束
    0.37
     দেড়
    0.37
    рави
    0.37
     заканчи
    0.37
    Act Density 0.004%

    No Known Activations