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

    Neuronpedia

    INDEX
    Explanations

    science and measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     United
    -0.07
    ард
    -0.07
     businesses
    -0.07
     кли
    -0.06
     Sé
    -0.06
    ارد
    -0.06
     volunte
    -0.06
     dav
    -0.06
    ard
    -0.06
    iami
    -0.06
    POSITIVE LOGITS
     Máy
    0.07
    '>
↵
    0.07
    軽
    0.06
     =>
↵
    0.06
    ">',↵
    0.06
    -qu
    0.06
    elmet
    0.06
     başka
    0.06
     viability
    0.06
     *)↵↵
    0.06
    Act Density 0.095%

    No Known Activations