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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WEEN
    -0.07
     Playing
    -0.06
     Scient
    -0.06
    <Renderer
    -0.06
     července
    -0.06
    /St
    -0.06
    地區
    -0.06
     spur
    -0.06
    amburger
    -0.06
    (IL
    -0.06
    POSITIVE LOGITS
    opp
    0.08
     dua
    0.07
    обрет
    0.07
    operands
    0.07
    故事
    0.06
     Pharmacy
    0.06
    πί
    0.06
     aeros
    0.06
    binary
    0.06
     exits
    0.06
    Act Density 0.001%

    No Known Activations