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

    Neuronpedia

    INDEX
    Explanations

    Country/culture categories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Form
    -0.07
     DEFIN
    -0.06
    Rs
    -0.06
    	LP
    -0.06
     уп
    -0.06
    VISION
    -0.06
     bak
    -0.06
    prepared
    -0.05
     WR
    -0.05
     Japan
    -0.05
    POSITIVE LOGITS
    ian
    0.08
    ovan
    0.07
    ürger
    0.07
    asis
    0.07
    embourg
    0.07
    ropsych
    0.07
     Rican
    0.07
     nons
    0.07
     uomini
    0.06
     พร
    0.06
    Act Density 0.021%

    No Known Activations