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

    Neuronpedia

    INDEX
    Explanations

    Foundation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Some
    -0.07
     pizza
    -0.06
    	    ↵
    -0.06
     violation
    -0.06
     Girls
    -0.06
    حيح
    -0.06
     /**↵
    -0.06
    �
    -0.06
    On
    -0.06
    资源
    -0.06
    POSITIVE LOGITS
     Foundation
    0.10
     end
    0.07
    URLException
    0.07
     foundation
    0.07
     WWW
    0.07
    بول
    0.07
    anking
    0.07
    _fil
    0.07
    acking
    0.07
     ас
    0.07
    Act Density 0.004%

    No Known Activations