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

    Neuronpedia

    INDEX
    Explanations

    jem

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    funcs
    -0.08
    发文
    -0.07
     hành
    -0.07
     بأنه
    -0.07
    /the
    -0.07
    Coverage
    -0.06
     +:+
    -0.06
    抢险
    -0.06
    .uf
    -0.06
     Quốc
    -0.06
    POSITIVE LOGITS
    どころ
    0.07
    >
↵
    0.07
     Điểm
    0.07
    EXTERNAL
    0.07
     gore
    0.07
    ﱊ
    0.06
     halten
    0.06
    肠
    0.06
    (food
    0.06
     Bake
    0.06
    Act Density 0.000%

    No Known Activations