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

    Neuronpedia

    INDEX
    Explanations

    machine, plan, SNS, image

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ænd
    0.52
     และ
    0.50
    ה
    0.48
    ढ़
    0.46
     [§
    0.44
     fruitful
    0.44
    ०
    0.44
    ≃
    0.44
    à
    0.43
     :-
    0.43
    POSITIVE LOGITS
     soybeans
    0.44
     Bureau
    0.41
     Xiao
    0.41
     soybean
    0.40
     ESPN
    0.40
    眼的
    0.40
     Lockheed
    0.40
    的情况
    0.39
     Soybean
    0.39
     vuelo
    0.38
    Act Density 0.000%

    No Known Activations