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

    Neuronpedia

    INDEX
    Explanations

    io

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BIG
    -0.07
    、何
    -0.07
    альних
    -0.07
    .ButterKnife
    -0.07
    ','');↵
    -0.06
    695
    -0.06
     lifting
    -0.06
    IPLE
    -0.06
    CLUSION
    -0.06
     Great
    -0.06
    POSITIVE LOGITS
     trai
    0.07
    /output
    0.06
     zih
    0.06
    ////////////////////////////////////////////////////////////////////
    0.06
    redux
    0.06
    [left
    0.06
     Messenger
    0.06
     je
    0.06
     Flyers
    0.06
    standen
    0.06
    Act Density 0.103%

    No Known Activations