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

    Neuronpedia

    INDEX
    Explanations

    Lisbon, Lisbeth, Liszt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jü
    0.42
     gf
    0.40
     Vf
    0.39
     Tat
    0.38
     syn
    0.37
    Schwe
    0.37
    eliti
    0.37
    沉
    0.37
     Bxc
    0.36
     Gus
    0.36
    POSITIVE LOGITS
     displays
    0.56
    Lis
    0.45
     display
    0.43
     lis
    0.42
    Displays
    0.42
    Display
    0.42
    displays
    0.42
    display
    0.41
    NMR
    0.40
    ఊ
    0.40
    Act Density 0.001%

    No Known Activations