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

    Neuronpedia

    INDEX
    Explanations

    history and time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.61
    DataAnnotations
    0.53
    ↵↵
    0.52
    ↵
    0.51
    ETTE
    0.50
    AIRE
    0.48
    ERRY
    0.47
    ことができます
    0.46
    ARTS
    0.46
    xC
    0.45
    POSITIVE LOGITS
    t
    0.69
     मोठ्या
    0.59
     pakistan
    0.56
    isjon
    0.55
     gått
    0.55
     جنگ
    0.53
    uestros
    0.52
     між
    0.52
     население
    0.51
     केल्यानंतर
    0.51
    Act Density 0.004%

    No Known Activations