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

    Neuronpedia

    INDEX
    Explanations

    odes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tours
    -0.07
     tours
    -0.06
    CreatedBy
    -0.06
     Sunset
    -0.06
     Οκ
    -0.06
     میلیون
    -0.06
    /image
    -0.06
    _MACHINE
    -0.06
     �
    -0.05
     personality
    -0.05
    POSITIVE LOGITS
    еш
    0.08
     ah
    0.07
    子
    0.07
    こ
    0.07
    opo
    0.07
    ,,,,,,,,
    0.06
     detox
    0.06
     Dough
    0.06
     왜
    0.06
     DNS
    0.06
    Act Density 0.002%

    No Known Activations