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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .hash
    -0.08
    没有什么
    -0.08
    uffman
    -0.07
    搬家
    -0.07
    iley
    -0.07
    -login
    -0.07
    toJson
    -0.07
    不想
    -0.07
     Chips
    -0.07
    新基建
    -0.07
    POSITIVE LOGITS
    포
    0.07
    库
    0.07
    �
    0.06
    ؾ
    0.06
     distorted
    0.06
     ???
    0.06
    ainted
    0.06
     standards
    0.06
     CONSTANT
    0.06
    _STRING
    0.06
    Act Density 0.001%

    No Known Activations