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

    Neuronpedia

    INDEX
    Explanations

    specific topics

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Di
    0.44
     Di
    0.44
    迪
    0.43
     Ya
    0.42
     디
    0.41
     دی
    0.39
     ди
    0.38
     di
    0.37
    دي
    0.37
    SelectedIndex
    0.36
    POSITIVE LOGITS
     wy
    0.39
     Hast
    0.39
    urgia
    0.36
    inflate
    0.36
    的一次
    0.36
     vy
    0.35
     hor
    0.35
     Say
    0.35
     zeg
    0.35
    jdt
    0.35
    Act Density 0.000%

    No Known Activations