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

    Neuronpedia

    INDEX
    Explanations

    say ") word"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    诗人
    -0.08
    Think
    -0.07
    	Key
    -0.07
     //================================================================
    -0.07
    読んで
    -0.07
    etzt
    -0.07
    >"
↵
    -0.06
    	Write
    -0.06
    怊
    -0.06
     Chúa
    -0.06
    POSITIVE LOGITS
     pioneered
    0.08
     Closure
    0.08
    ارد
    0.07
    уль
    0.07
    _bd
    0.07
    jem
    0.07
     %(
    0.07
     advisor
    0.06
    Closure
    0.06
    IEL
    0.06
    Act Density 0.044%

    No Known Activations