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

    Neuronpedia

    INDEX
    Explanations

    IT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    277
    -0.06
     Ein
    -0.06
    Af
    -0.06
     ITER
    -0.06
     salmon
    -0.06
    ۱۹۸
    -0.06
    اید
    -0.06
    stinian
    -0.06
    PLETED
    -0.06
    еної
    -0.05
    POSITIVE LOGITS
     Brock
    0.13
    .CompilerServices
    0.08
    rock
    0.07
    /theme
    0.07
    angel
    0.07
     Tep
    0.07
     bartender
    0.07
    .round
    0.07
     tumblr
    0.07
     bart
    0.06
    Act Density 0.005%

    No Known Activations