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

    Neuronpedia

    INDEX
    Explanations

    [:

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (feature
    -0.08
     Juan
    -0.08
     Appeals
    -0.08
    的关注
    -0.07
    _fifo
    -0.07
    _JO
    -0.07
    .sf
    -0.07
     viral
    -0.07
     Suzanne
    -0.06
    lds
    -0.06
    POSITIVE LOGITS
    選�
    0.08
     currentIndex
    0.07
     selectedIndex
    0.07
    يلة
    0.07
     resid
    0.07
    [:
    0.06
    ǥ
    0.06
    早上
    0.06
    blers
    0.06
    初三
    0.06
    Act Density 0.004%

    No Known Activations