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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -game
    -0.07
     Horizon
    -0.07
     Friends
    -0.07
    Friends
    -0.07
    ÜRK
    -0.07
     Jones
    -0.07
     renting
    -0.06
    translate
    -0.06
    	The
    -0.06
     InterruptedException
    -0.06
    POSITIVE LOGITS
     Společ
    0.06
     quirky
    0.06
    .github
    0.06
    醫
    0.06
    Sab
    0.06
    gium
    0.05
    相信
    0.05
    .To
    0.05
     conced
    0.05
    방법
    0.05
    Act Density 0.029%

    No Known Activations