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

    Neuronpedia

    INDEX
    Explanations

    favor or advantage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ாண
    0.42
    orgt
    0.41
     распро
    0.38
    跺
    0.37
    哃
    0.37
     موجودگی
    0.37
    otong
    0.36
    isio
    0.35
    isert
    0.35
     അതേ
    0.35
    POSITIVE LOGITS
     favour
    1.76
     favoring
    1.74
     favor
    1.69
    favor
    1.50
     favours
    1.49
     favors
    1.47
    Favor
    1.47
     Favor
    1.42
     favore
    1.37
     favorable
    1.30
    Act Density 0.018%

    No Known Activations