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

    Neuronpedia

    INDEX
    Explanations

    say "number 3"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getUsers
    -0.07
    笃
    -0.07
     gated
    -0.07
     GetAll
    -0.07
     fundamental
    -0.07
     clinging
    -0.07
    yne
    -0.07
    晓得
    -0.07
     получен
    -0.07
    mlink
    -0.06
    POSITIVE LOGITS
    February
    0.07
     historia
    0.07
    плачива
    0.07
    Australian
    0.07
    ,U
    0.06
    _prices
    0.06
    COVER
    0.06
    作为一个
    0.06
    史上
    0.06
    历史上
    0.06
    Act Density 0.002%

    No Known Activations