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

    Neuronpedia

    INDEX
    Explanations

    element

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yyy
    -0.07
    bagai
    -0.06
     Sox
    -0.06
     nuru
    -0.06
    np
    -0.06
     thriving
    -0.06
     Miy
    -0.06
    'clock
    -0.06
     rainy
    -0.06
    海外
    -0.06
    POSITIVE LOGITS
     که
    0.08
    leg
    0.07
     покуп
    0.07
    ีก
    0.07
    CUR
    0.07
     Ticaret
    0.06
    ental
    0.06
    LOB
    0.06
    LEG
    0.06
     solo
    0.06
    Act Density 0.005%

    No Known Activations