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

    Neuronpedia

    INDEX
    Explanations

    excited

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Oman
    -0.07
    reek
    -0.07
    oğlu
    -0.07
     lạ
    -0.07
    -0.07
    )){
↵
    -0.06
    ABCDEFGHIJKLMNOP
    -0.06
    时代
    -0.06
     managerial
    -0.06
    甘
    -0.06
    POSITIVE LOGITS
     excited
    0.16
    狠
    0.07
     استاند
    0.06
     veloc
    0.06
    )index
    0.06
    [Index
    0.06
     luckily
    0.06
    error
    0.06
     앉
    0.06
    IC
    0.06
    Act Density 0.006%

    No Known Activations