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

    Neuronpedia

    INDEX
    Explanations

    enjoy the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     حوصل
    0.59
     अगर
    0.54
     سبب
    0.54
    Sites
    0.53
    කට
    0.53
    '।
    0.53
     règles
    0.52
     razão
    0.52
     ibn
    0.52
    DEFINITION
    0.52
    POSITIVE LOGITS
    ва
    0.86
    the
    0.86
    it
    0.76
    ਰ
    0.68
    享受
    0.63
    ما
    0.61
     enjoyed
    0.59
    t
    0.57
     enjoy
    0.56
     pleinement
    0.56
    Act Density 0.055%

    No Known Activations