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

    Neuronpedia

    INDEX
    Explanations

    ver

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    帝王
    -0.07
    内部控制
    -0.07
     on
    -0.07
     stride
    -0.07
    "That
    -0.07
    uis
    -0.07
    -this
    -0.07
    .populate
    -0.07
    Narrated
    -0.07
    itled
    -0.07
    POSITIVE LOGITS
    挥发
    0.08
     Whip
    0.07
     fermentation
    0.07
     locking
    0.07
    NotEmpty
    0.07
    纪委监委
    0.07
    igs
    0.07
     prosecutions
    0.07
     Testament
    0.07
     ""))↵
    0.07
    Act Density 0.027%

    No Known Activations