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

    Neuronpedia

    INDEX
    Explanations

    fish species names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wat
    -0.07
    predicted
    -0.07
    基础
    -0.07
     subordinate
    -0.07
     Wide
    -0.07
    コミュニ
    -0.07
    ならない
    -0.07
     cũ
    -0.07
    _INTER
    -0.07
    主旨
    -0.07
    POSITIVE LOGITS
     *@
    0.08
    ",@"
    0.07
    _Method
    0.07
    ":@"
    0.07
    IOUS
    0.07
    ₂
    0.07
    .between
    0.07
    *>
    0.07
    腿部
    0.07
    (that
    0.06
    Act Density 0.007%

    No Known Activations