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

    Neuronpedia

    INDEX
    Explanations

    conjunction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    积极响应
    -0.07
     persever
    -0.07
    _pixels
    -0.07
    这么多
    -0.07
    受理
    -0.07
     paperback
    -0.07
     jackpot
    -0.07
     heavily
    -0.07
     !↵
    -0.06
    .Relative
    -0.06
    POSITIVE LOGITS
    xdf
    0.08
     enums
    0.07
    淮
    0.07
    命令
    0.07
     Armour
    0.07
    }}{{
    0.07
     administrators
    0.07
    ,col
    0.07
     unusual
    0.06
     "\""
    0.06
    Act Density 0.004%

    No Known Activations