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

    Neuronpedia

    INDEX
    Explanations

    tracking levels or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onese
    0.42
    圈
    0.38
     도형
    0.38
    ational
    0.37
     항상
    0.37
    ene
    0.36
     후
    0.36
    wr
    0.35
     марке
    0.35
    inars
    0.35
    POSITIVE LOGITS
     fortifications
    0.42
     ANZ
    0.41
    䣰
    0.40
     should
    0.40
     szpital
    0.38
     reforms
    0.38
     anz
    0.38
     Rental
    0.38
    riu
    0.38
    瀹
    0.38
    Act Density 0.000%

    No Known Activations