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

    Neuronpedia

    INDEX
    Explanations

    administrative divisions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tons
    -0.07
    力を
    -0.06
     شهید
    -0.06
    .INVALID
    -0.06
     半
    -0.06
     /**↵
    -0.06
    :"-"`↵
    -0.06
     exploits
    -0.06
    ذ
    -0.06
     reputation
    -0.06
    POSITIVE LOGITS
     CGI
    0.08
    	TRACE
    0.08
     surname
    0.07
     --->
    0.07
     М
    0.06
    TJ
    0.06
     piercing
    0.06
    antry
    0.06
    -num
    0.06
     ipAddress
    0.06
    Act Density 0.038%

    No Known Activations