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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages/encoded text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     moje
    -0.08
     Ris
    -0.08
     Tales
    -0.08
     Pra
    -0.08
    linux
    -0.08
     Myself
    -0.08
     */↵//
    -0.08
     실
    -0.08
     poul
    -0.08
     Miranda
    -0.07
    POSITIVE LOGITS
    ୍
    0.08
    �
    0.08
    .endswith
    0.08
    %E
    0.08
    ​
    0.08
    �
    0.08
    \xc
    0.08
     କ
    0.08
    /gallery
    0.07
    �
    0.07
    Act Density 0.035%

    No Known Activations