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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    undry
    -0.08
     credited
    -0.06
     lubric
    -0.06
     novels
    -0.06
    vající
    -0.06
    ชนะ
    -0.06
     Wine
    -0.06
    loader
    -0.06
     CLK
    -0.06
    ouses
    -0.06
    POSITIVE LOGITS
    )
    0.08
     tý
    0.07
    ))
    0.07
    ]]>
    0.07
    亿
    0.07
    サー
    0.06
     。
    0.06
     tent
    0.06
     (
    0.06
    ){
    0.06
    Act Density 0.010%

    No Known Activations