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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _feature
    -0.07
    чивается
    -0.07
     selected
    -0.07
     magnificent
    -0.07
    retty
    -0.07
    ست
    -0.06
    HWND
    -0.06
    тал
    -0.06
     temsil
    -0.06
     Теп
    -0.06
    POSITIVE LOGITS
     deadliest
    0.06
    áln
    0.06
     plusieurs
    0.06
     Hunters
    0.06
     SSR
    0.06
     ),
↵
    0.06
    );?>↵
    0.06
     еп
    0.05
    preh
    0.05
    <ApplicationUser
    0.05
    Act Density 0.036%

    No Known Activations