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

    Neuronpedia

    INDEX
    Explanations

    DIRECT

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     occasions
    -0.07
    scrição
    -0.07
     הכנסת
    -0.07
    �
    -0.07
    😥
    -0.07
    搜索
    -0.07
    coc
    -0.07
     manufactured
    -0.07
    😪
    -0.07
    orch
    -0.07
    POSITIVE LOGITS
    OPTION
    0.07
    HOW
    0.07
    ił
    0.07
    they
    0.07
    ndon
    0.07
    .How
    0.07
    Atoms
    0.07
    оля
    0.06
    лага
    0.06
    Ideal
    0.06
    Act Density 0.001%

    No Known Activations