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

    Neuronpedia

    INDEX
    Explanations

    Stephen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mice
    -0.07
     zaj
    -0.06
     Monroe
    -0.06
     �
    -0.06
     بندی
    -0.06
     řek
    -0.06
     được
    -0.06
     toolkit
    -0.06
     Mansion
    -0.06
    =\"";↵
    -0.06
    POSITIVE LOGITS
     chefs
    0.07
     rods
    0.07
    <context
    0.07
    .fm
    0.07
    ino
    0.07
     inappropriate
    0.07
    cho
    0.07
     Moves
    0.06
     stup
    0.06
     Steve
    0.06
    Act Density 0.006%

    No Known Activations