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

    Neuronpedia

    INDEX
    Explanations

    prompt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mind
    -0.09
     founded
    -0.09
     coined
    -0.08
     daim
    -0.08
     smooth
    -0.08
     Founded
    -0.07
     blog
    -0.07
     mixed
    -0.07
     fans
    -0.07
     according
    -0.07
    POSITIVE LOGITS
    _TEMPLATE
    0.09
     Vorlage
    0.09
     Rece
    0.09
     Rochelle
    0.09
    	template
    0.08
    お願い
    0.08
    模板
    0.08
    <|start|>
    0.08
     beoord
    0.08
    			
↵			
↵
    0.08
    Act Density 0.007%

    No Known Activations