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

    Neuronpedia

    INDEX
    Explanations

    delivery duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     लैस
    0.76
    擂
    0.73
     toned
    0.72
     Επι
    0.70
     retrato
    0.70
    levelup
    0.68
     Punkt
    0.67
    嶇
    0.66
     escena
    0.66
    吶
    0.66
    POSITIVE LOGITS
     duration
    3.00
     durations
    2.84
    Duration
    2.77
    duration
    2.75
     Duration
    2.74
     기간
    2.56
     duración
    2.45
     durée
    2.42
     durata
    2.38
     length
    2.30
    Act Density 0.791%

    No Known Activations