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

    Neuronpedia

    INDEX
    Explanations

    units of time and length

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     टाकी
    0.36
    ிரம்
    0.36
    ளின்
    0.35
     Simultaneous
    0.34
    思い
    0.33
    働き
    0.33
     Both
    0.33
    ...">
    0.33
    ద్
    0.33
     Gm
    0.33
    POSITIVE LOGITS
    months
    0.48
     exact
    0.48
     eleven
    0.47
     months
    0.47
     minutes
    0.46
    minutes
    0.45
    Months
    0.45
     ۶
    0.44
     डेढ़
    0.43
     thirteen
    0.43
    Act Density 0.012%

    No Known Activations