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

    Neuronpedia

    INDEX
    Explanations

    Like you/me

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stances
    -0.07
     Jake
    -0.07
    loaded
    -0.06
    Jake
    -0.06
     Latin
    -0.06
     sneakers
    -0.06
     onView
    -0.06
    alah
    -0.06
    ander
    -0.06
    inya
    -0.06
    POSITIVE LOGITS
     litres
    0.07
     presenter
    0.07
    究
    0.06
     руковод
    0.06
    	run
    0.06
    ?>><?
    0.06
     Edu
    0.06
    앤
    0.06
    ;
↵
↵
↵
↵
    0.06
     zdravot
    0.06
    Act Density 0.018%

    No Known Activations