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

    Neuronpedia

    INDEX
    Explanations

    Because

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marcos
    -0.07
    اهرة
    -0.06
     съ
    -0.06
    анд
    -0.06
     Allah
    -0.06
    imizer
    -0.06
    endcode
    -0.06
     نع
    -0.06
    ъ
    -0.06
     Wednesday
    -0.06
    POSITIVE LOGITS
    ेक
    0.07
    ;↵↵↵↵↵
    0.07
    -esteem
    0.07
    Dem
    0.07
    Fre
    0.07
    sites
    0.06
    780
    0.06
    üstü
    0.06
     babes
    0.06
    857
    0.06
    Act Density 0.016%

    No Known Activations