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

    Neuronpedia

    INDEX
    Explanations

    Niche topics becoming widespread

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prés
    -0.07
    픠
    -0.07
    请您
    -0.07
     nombreux
    -0.07
    forme
    -0.07
    imizer
    -0.06
     province
    -0.06
     Proceedings
    -0.06
    通知书
    -0.06
    主公
    -0.06
    POSITIVE LOGITS
     stuffing
    0.08
     tắm
    0.07
     раств
    0.07
    Manufact
    0.07
    打卡
    0.07
     clap
    0.07
    Sampling
    0.06
     słab
    0.06
    漱
    0.06
    .Read
    0.06
    Act Density 0.036%

    No Known Activations