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

    Neuronpedia

    INDEX
    Explanations

    XML namespace URIs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tranquilidad
    0.55
     teinture
    0.52
    zoomSeekBar
    0.52
     McCullough
    0.50
     vulve
    0.49
     diarrh
    0.49
    áfico
    0.49
     грошы
    0.48
    混凝
    0.48
     ወቅ
    0.47
    POSITIVE LOGITS
    n
    0.55
    j
    0.53
    中国
    0.52
    c
    0.51
    t
    0.50
    Display
    0.47
     =
    0.47
    trim
    0.47
    美国
    0.46
    xmlns
    0.46
    Act Density 0.005%

    No Known Activations