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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ними
    -0.08
    جمع
    -0.07
     کیفیت
    -0.07
    Columns
    -0.06
     Illinois
    -0.06
    ��
    -0.06
     realizado
    -0.06
    HEN
    -0.06
    tracks
    -0.06
    mission
    -0.06
    POSITIVE LOGITS
    .Print
    0.06
    ieved
    0.06
     Луч
    0.06
    YGON
    0.06
    ,end
    0.06
    .doc
    0.06
     disrupting
    0.06
    739
    0.06
    logout
    0.06
    険
    0.06
    Act Density 0.001%

    No Known Activations