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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seasoned
    -0.07
     discarded
    -0.07
    Iso
    -0.07
     -----↵
    -0.07
     Rub
    -0.07
    iciencies
    -0.07
    看不懂
    -0.07
    学子
    -0.07
     Larson
    -0.06
     utiliza
    -0.06
    POSITIVE LOGITS
    一样
    0.06
    ViewState
    0.06
    declar
    0.06
    /modules
    0.06
     weapons
    0.06
    防空
    0.06
     thăm
    0.06
    .createParallelGroup
    0.06
    大学
    0.06
    .gradle
    0.06
    Act Density 0.042%

    No Known Activations