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

    Neuronpedia

    INDEX
    Explanations

    your you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     handles
    0.45
     chunks
    0.44
     collections
    0.42
     parity
    0.42
     substantial
    0.40
     parsing
    0.39
     samples
    0.39
     con
    0.39
    (
    0.39
     exhaust
    0.39
    POSITIVE LOGITS
    あなたの
    0.88
    your
    0.82
     당신
    0.82
    Your
    0.79
    你的
    0.79
     あなた
    0.76
    あなたが
    0.75
     Você
    0.74
     вашей
    0.74
    あなた
    0.73
    Act Density 0.395%

    No Known Activations