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
    듬
    -0.07
    .breakpoints
    -0.07
    精益求
    -0.07
    稳步
    -0.07
    钱财
    -0.07
     ^{↵
    -0.06
     formally
    -0.06
    ไล
    -0.06
    ursively
    -0.06
     fisse
    -0.06
    POSITIVE LOGITS
    含量
    0.07
    protein
    0.07
    应急
    0.07
     Secretary
    0.07
    應該
    0.07
     Mu
    0.07
    vert
    0.06
    谓
    0.06
     такой
    0.06
     Judgment
    0.06
    Act Density 0.114%

    No Known Activations