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

    Neuronpedia

    INDEX
    Explanations

    Delta

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     통해
    -0.07
    ılmış
    -0.07
     작성
    -0.06
     wenig
    -0.06
    ummer
    -0.06
    .AlertDialog
    -0.06
    一个人
    -0.06
    笑
    -0.06
    Subviews
    -0.06
     Pricing
    -0.06
    POSITIVE LOGITS
    ETA
    0.08
     Blue
    0.07
    aber
    0.07
     blue
    0.07
    ernal
    0.07
     Morph
    0.07
     dieta
    0.07
    igrate
    0.06
    Elem
    0.06
     дор
    0.06
    Act Density 0.000%

    No Known Activations