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

    Neuronpedia

    INDEX
    Explanations

    cli

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tle
    -0.08
    قد
    -0.07
      
↵
↵
    -0.07
    HEN
    -0.07
    bt
    -0.07
     tissues
    -0.07
    ᴼ
    -0.07
     on
    -0.07
    fv
    -0.07
    눱
    -0.07
    POSITIVE LOGITS
    三角
    0.07
    ﱇ
    0.07
    מילה
    0.07
    -Mart
    0.07
     полит
    0.07
     ROUT
    0.06
    𣷭
    0.06
     ц
    0.06
     ори
    0.06
    𝕘
    0.06
    Act Density 0.003%

    No Known Activations