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

    Neuronpedia

    INDEX
    Explanations

    introduction to explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inel
    0.54
     Bhagavato
    0.52
    <unused1158>
    0.52
     निहित
    0.51
     ପ୍ର
    0.50
    dır
    0.49
    <unused647>
    0.49
    norm
    0.48
     总
    0.48
    <unused1003>
    0.48
    POSITIVE LOGITS
     eaten
    0.52
    ("
    0.43
     Spain
    0.42
     bonuses
    0.42
    ব
    0.40
    ボ
    0.40
     slowly
    0.39
    ก
    0.39
    !)
    0.38
     eat
    0.38
    Act Density 0.001%

    No Known Activations