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

    Neuronpedia

    INDEX
    Explanations

    time management and periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilevel
    0.91
     humo
    0.83
     lifelong
    0.82
    तम
    0.77
    time
    0.76
     timely
    0.76
    ときの
    0.75
    当時の
    0.73
     financier
    0.72
     químicos
    0.72
    POSITIVE LOGITS
     суток
    1.52
    frames
    1.45
     frame
    1.37
    戳
    1.34
     honored
    1.33
     honoured
    1.29
    মতো
    1.26
     lapse
    1.25
    pieces
    1.25
    frame
    1.21
    Act Density 0.188%

    No Known Activations