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

    Neuronpedia

    INDEX
    Explanations

    Legal obligations and failures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ნის
    -0.09
    ორის
    -0.09
    Birth
    -0.09
    რის
    -0.09
    რც
    -0.09
    ახებ
    -0.08
    ონის
    -0.08
    ეხ
    -0.08
     нужны
    -0.08
     artists
    -0.08
    POSITIVE LOGITS
    ofd
    0.09
     Honestly
    0.09
     Attempt
    0.09
     raisonn
    0.08
    努力
    0.08
     razon
    0.08
     försö
    0.08
     प्रयास
    0.08
     honestly
    0.08
     ശ്രമ
    0.08
    Act Density 0.048%

    No Known Activations