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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tw
    -0.07
     ハ
    -0.06
     Кол
    -0.06
     Sixth
    -0.06
    getitem
    -0.06
    八
    -0.06
     Guardian
    -0.06
     Dead
    -0.06
    �
    -0.06
    сю
    -0.06
    POSITIVE LOGITS
    ">@
    0.07
    ",$
    0.07
    _migration
    0.07
    ='".$
    0.07
     �
    0.06
    权限
    0.06
    aira
    0.06
     삼성
    0.06
     cih
    0.06
    `"]↵
    0.06
    Act Density 0.035%

    No Known Activations