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

    Neuronpedia

    INDEX
    Explanations

    back

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    роб
    -0.08
     vorhanden
    -0.07
     susceptibility
    -0.07
     лид
    -0.07
    .Localization
    -0.07
    иль
    -0.07
     tính
    -0.07
    .execute
    -0.07
     exist
    -0.07
     vertices
    -0.07
    POSITIVE LOGITS
    �
    0.09
    То
    0.08
     cheering
    0.08
    看的
    0.08
     hateful
    0.08
    欢
    0.08
     তাক
    0.08
     назад
    0.08
    Cheers
    0.08
     splend
    0.08
    Act Density 0.003%

    No Known Activations