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

    Neuronpedia

    INDEX
    Explanations

    wonder and wonderful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     জিৎ
    0.40
    0.39
    าท
    0.39
     검
    0.36
    जित
    0.36
     magnetic
    0.35
     причин
    0.35
    agnetic
    0.35
    结局
    0.35
    ပြု
    0.35
    POSITIVE LOGITS
    Wonder
    3.14
     Wonder
    3.09
     wonder
    3.05
    wonder
    2.86
     wonders
    2.53
     Wonders
    2.47
    Wonderful
    2.22
     wondered
    2.19
     Wonderland
    2.17
     Wonderful
    2.16
    Act Density 0.035%

    No Known Activations