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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _space
    -0.07
     Rahul
    -0.07
     hinge
    -0.06
     yer
    -0.06
     прибы
    -0.06
     Shar
    -0.06
     intim
    -0.06
     ASA
    -0.06
    牛
    -0.06
     леч
    -0.06
    POSITIVE LOGITS
    Ë
    0.07
    (mem
    0.07
     �
    0.06
    üb
    0.06
    -floating
    0.06
    ELCOME
    0.06
     pname
    0.06
    ‑
    0.06
    �
    0.06
    .IO
    0.06
    Act Density 0.277%

    No Known Activations