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

    Neuronpedia

    INDEX
    Explanations

    over time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Timeline
    0.41
     timeline
    0.41
    Timeline
    0.40
    timeline
    0.37
     TIMESTAMP
    0.36
    Timothy
    0.35
     TimeUnit
    0.35
     Related
    0.34
    TimeUnit
    0.34
     BASED
    0.34
    POSITIVE LOGITS
    whelming
    0.48
     Gradually
    0.45
     time
    0.44
     whe
    0.44
     постепенно
    0.44
    дування
    0.44
    coming
    0.43
    cando
    0.43
     время
    0.42
     ensuing
    0.42
    Act Density 0.007%

    No Known Activations