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

    Neuronpedia

    INDEX
    Explanations

    explaining concepts or reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    所有
    0.53
     所有
    0.51
     عن
    0.50
     من
    0.49
     所以
    0.49
     سر
    0.49
     പുതിയ
    0.47
     buono
    0.46
     all
    0.46
    endimento
    0.46
    POSITIVE LOGITS
     també
    0.48
    ﺔ
    0.46
     ALSO
    0.45
    者が
    0.45
    :
    0.44
     incentiv
    0.44
    者を
    0.44
    a
    0.44
     recourse
    0.42
     öner
    0.42
    Act Density 0.001%

    No Known Activations