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

    Neuronpedia

    INDEX
    Explanations

    XX male, Xia's existence, fungus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     시작
    0.44
     बालिका
    0.44
     уйный
    0.43
     배경
    0.43
    Minus
    0.43
     확률
    0.43
    StarCore
    0.42
     EXIST
    0.42
    ścic
    0.42
    퀀
    0.42
    POSITIVE LOGITS
    ster
    0.49
    ra
    0.46
    '
    0.46
     etc
    0.44
    7
    0.43
     soap
    0.42
     kullanım
    0.42
    6
    0.42
    ura
    0.42
    dont
    0.41
    Act Density 0.009%

    No Known Activations