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

    Neuronpedia

    INDEX
    Explanations

    -use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tak
    -0.07
    ypo
    -0.07
    appable
    -0.07
     numeros
    -0.07
    bar
    -0.06
    “And
    -0.06
     Xia
    -0.06
    如此
    -0.06
     MOM
    -0.06
    cko
    -0.06
    POSITIVE LOGITS
    persistent
    0.07
    登录
    0.07
     conhe
    0.07
    댑
    0.07
     layered
    0.07
     lowered
    0.07
     società
    0.07
    .cart
    0.06
    人人都
    0.06
    完全
    0.06
    Act Density 0.000%

    No Known Activations