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

    Neuronpedia

    INDEX
    Explanations

    code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     neces
    -0.08
     QC
    -0.07
     Lud
    -0.07
     Brands
    -0.07
    啪
    -0.07
    ț
    -0.06
    梦
    -0.06
     NIGHT
    -0.06
    resident
    -0.06
    BH
    -0.06
    POSITIVE LOGITS
    	search
    0.07
     بالاتر
    0.07
     léč
    0.06
     ΕΠ
    0.06
     Furious
    0.06
    /http
    0.06
     澳
    0.06
    creen
    0.06
     ​​​
    0.06
     Disabilities
    0.06
    Act Density 0.000%

    No Known Activations