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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    虑
    -0.07
    要知道
    -0.07
    قود
    -0.07
    株
    -0.07
    歲
    -0.07
     occurring
    -0.06
    级
    -0.06
     Achie
    -0.06
    gni
    -0.06
     луч
    -0.06
    POSITIVE LOGITS
     =================================================
    0.07
    istor
    0.07
    ]',
    0.07
    BSD
    0.07
    提振
    0.06
    lexer
    0.06
    FromBody
    0.06
    (defvar
    0.06
    ipv
    0.06
    ويد
    0.06
    Act Density 0.045%

    No Known Activations