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

    Neuronpedia

    INDEX
    Explanations

    repro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    |m
    -0.07
    (J
    -0.07
     lekker
    -0.07
    lies
    -0.07
    他是
    -0.07
    奖励
    -0.07
    _udp
    -0.07
    "T
    -0.07
    ";↵↵↵
    -0.07
    Judge
    -0.06
    POSITIVE LOGITS
    -shop
    0.08
     calend
    0.07
    𝔬
    0.07
     manufact
    0.07
     picks
    0.07
    wró
    0.07
    �
    0.07
     adicion
    0.07
    𝘖
    0.06
     Picks
    0.06
    Act Density 0.001%

    No Known Activations