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

    Neuronpedia

    INDEX
    Explanations

    -packages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kaydet
    -0.06
     Мон
    -0.06
    ,.
    -0.06
     freshwater
    -0.06
     〃
    -0.05
     republice
    -0.05
    ';';
    -0.05
    Claims
    -0.05
     curt
    -0.05
    edelta
    -0.05
    POSITIVE LOGITS
    -packages
    0.08
    (Blueprint
    0.07
    -create
    0.07
    Um
    0.06
     purge
    0.06
     ):↵↵
    0.06
    -r
    0.06
    ис
    0.06
    -called
    0.06
     Sword
    0.06
    Act Density 0.001%

    No Known Activations