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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ;
    -0.08
     các
    -0.07
     ਬ
    -0.07
     централь
    -0.07
     chiens
    -0.07
     challeng
    -0.07
     lång
    -0.07
    ");↵↵
    -0.07
     chefs
    -0.07
    /photos
    -0.07
    POSITIVE LOGITS
     zusätzlichen
    0.08
    elerik
    0.08
     siquiera
    0.08
     Additional
    0.08
    anium
    0.08
    0.08
    iteur
    0.08
     अतिरिक्त
    0.08
    idosis
    0.08
    ecutable
    0.08
    Act Density 0.103%

    No Known Activations