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

    Neuronpedia

    INDEX
    Explanations

    C++ code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اجع
    -0.07
    Won
    -0.07
    uto
    -0.07
     lxml
    -0.07
    its
    -0.06
    電影
    -0.06
     человек
    -0.06
     Minist
    -0.06
     refurb
    -0.06
    hunt
    -0.06
    POSITIVE LOGITS
     inventive
    0.06
    uerdo
    0.06
    �
    0.06
    Serv
    0.06
     yerde
    0.06
     cria
    0.06
     Odd
    0.06
    Hy
    0.06
    /us
    0.06
    ोज
    0.06
    Act Density 0.004%

    No Known Activations