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

    Neuronpedia

    INDEX
    Explanations

    pdf html

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Klopp
    -0.07
     IReadOnly
    -0.07
     Weiner
    -0.07
     використов
    -0.07
    �u
    -0.06
     Frankfurt
    -0.06
     varargin
    -0.06
    ひと
    -0.06
     जबक
    -0.06
     treadmill
    -0.06
    POSITIVE LOGITS
    pin
    0.07
     Attend
    0.07
     horribly
    0.07
    never
    0.06
     Ze
    0.06
    ‚
    0.06
     Pow
    0.06
    олуч
    0.06
    <Message
    0.06
    jam
    0.06
    Act Density 0.026%

    No Known Activations