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

    Neuronpedia

    INDEX
    Explanations

    stream

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bard
    -0.06
     Bread
    -0.06
    _memory
    -0.06
    —you
    -0.06
     ekran
    -0.06
     Mayer
    -0.06
     Silver
    -0.06
    ユ
    -0.06
     خشک
    -0.06
     Dude
    -0.06
    POSITIVE LOGITS
     Gst
    0.08
     insist
    0.07
     NSUInteger
    0.07
     opts
    0.07
    менно
    0.07
     Ancient
    0.06
    trag
    0.06
    strict
    0.06
     LGBT
    0.06
    影响
    0.06
    Act Density 0.001%

    No Known Activations