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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    628
    -0.06
    ony
    -0.06
     Geek
    -0.06
    ΑΔ
    -0.06
     nuances
    -0.06
    oples
    -0.06
     RECORD
    -0.06
    702
    -0.06
     Champions
    -0.06
    τσ
    -0.06
    POSITIVE LOGITS
     beaucoup
    0.08
     fost
    0.07
     <![
    0.07
    ندگی
    0.07
     drought
    0.07
    getNum
    0.07
     zároveň
    0.06
     snork
    0.06
    دید
    0.06
    *)(
    0.06
    Act Density 0.018%

    No Known Activations