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

    Neuronpedia

    INDEX
    Explanations

    routines and habits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    实际
    0.46
    ieke
    0.42
     হলাম
    0.42
     oranı
    0.41
     ситуа
    0.41
     अनुभ
    0.41
    actual
    0.41
    ijker
    0.40
     nyata
    0.40
    entukan
    0.40
    POSITIVE LOGITS
     routine
    0.66
     reportedly
    0.66
    routine
    0.64
     Routine
    0.63
    Routine
    0.61
     είχε
    0.59
     rutina
    0.58
     seemed
    0.56
     toxicology
    0.56
     suspicious
    0.56
    Act Density 0.012%

    No Known Activations