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

    Neuronpedia

    INDEX
    Explanations

    Step

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ству
    -0.07
     isVisible
    -0.06
     Vanderbilt
    -0.06
     rooftop
    -0.06
     App
    -0.06
     Am
    -0.06
    _rooms
    -0.06
    maal
    -0.06
    (opts
    -0.06
     lear
    -0.06
    POSITIVE LOGITS
    /*----------------------------------------------------------------------------
    0.06
     hur
    0.06
     Clara
    0.06
     hiçbir
    0.06
    тери
    0.06
     fashioned
    0.06
     souha
    0.06
    Quiz
    0.06
     Lebens
    0.06
     environmental
    0.06
    Act Density 0.017%

    No Known Activations