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

    Neuronpedia

    INDEX
    Explanations

    portable

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    пущен
    -0.07
    밥
    -0.07
    usk
    -0.07
    add
    -0.07
    过了
    -0.07
     qua
    -0.07
    aidu
    -0.07
     nouvelle
    -0.07
     wealth
    -0.07
     publié
    -0.06
    POSITIVE LOGITS
    绚丽
    0.07
    ');?>"
    0.07
    洁
    0.07
     Filip
    0.07
    edelta
    0.06
     Jab
    0.06
     Compact
    0.06
     Picture
    0.06
     licence
    0.06
    /$',
    0.06
    Act Density 0.005%

    No Known Activations