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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mary
    -0.08
     Mary
    -0.08
    ới
    -0.07
     从
    -0.07
     Mas
    -0.07
    ariance
    -0.07
    ToFront
    -0.07
     wich
    -0.06
     Бі
    -0.06
     cents
    -0.06
    POSITIVE LOGITS
    endent
    0.06
    ακ
    0.06
    solution
    0.06
    ैं.
    0.06
     spot
    0.06
    uffer
    0.06
     bộ
    0.06
    DropDown
    0.06
     hole
    0.06
    ního
    0.06
    Act Density 0.000%

    No Known Activations