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

    Neuronpedia

    INDEX
    Explanations

    dietary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     내
    -0.07
    ��
    -0.06
     bolest
    -0.06
    wind
    -0.06
     unofficial
    -0.06
    ，以及
    -0.06
    tutorial
    -0.06
     cork
    -0.06
     вже
    -0.06
     Taj
    -0.06
    POSITIVE LOGITS
     ocup
    0.07
    IES
    0.07
     commodity
    0.07
     aspiration
    0.07
    (con
    0.07
    ummings
    0.07
    Feb
    0.06
    Alan
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
     Kaepernick
    0.06
    Act Density 0.019%

    No Known Activations