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

    Neuronpedia

    INDEX
    Explanations

    fake or disguise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    酥
    0.46
     breaths
    0.46
    Là
    0.46
     commenters
    0.45
    酺
    0.44
    的一切
    0.44
     INVESTMENT
    0.43
    的時間
    0.42
    స్తు
    0.42
     Eintritt
    0.42
    POSITIVE LOGITS
     deceit
    0.54
     paura
    0.51
    偽
    0.47
     fake
    0.47
     deception
    0.45
     disguise
    0.43
     pretended
    0.42
    でも
    0.42
     disguised
    0.42
     disgu
    0.41
    Act Density 0.006%

    No Known Activations