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

    Neuronpedia

    INDEX
    Explanations

    playing or current flow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ఇటీ
    0.40
    媇
    0.39
     หัด
    0.38
    CLASSES
    0.37
     dama
    0.37
    ERCE
    0.37
    IDTH
    0.37
    UTILS
    0.37
    ⅱ
    0.37
    蒌
    0.37
    POSITIVE LOGITS
     Play
    0.49
     played
    0.48
     play
    0.48
    play
    0.48
    played
    0.44
    播放
    0.43
     playing
    0.42
    playing
    0.42
     n
    0.41
    num
    0.40
    Act Density 0.000%

    No Known Activations