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

    Neuronpedia

    INDEX
    Explanations

    as mentioned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ئیں۔
    0.70
    '.
    0.67
     nonetheless
    0.65
    .\
    0.65
    分别为
    0.64
     ако
    0.63
    ().
    0.63
    ziehungs
    0.63
    只要
    0.63
    Medium
    0.63
    POSITIVE LOGITS
     mentioned
    1.57
     mencionado
    1.31
     stated
    1.29
     previously
    1.20
     alluded
    1.16
     erwähnt
    1.15
     noted
    1.13
     said
    1.10
     mencion
    1.09
    mentioned
    1.08
    Act Density 0.045%

    No Known Activations