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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    required
    -0.07
    COVID
    -0.06
    Moder
    -0.06
     Rings
    -0.06
     Humanity
    -0.06
     Attorney
    -0.06
    україн
    -0.06
     Devil
    -0.06
     JP
    -0.06
     enriched
    -0.06
    POSITIVE LOGITS
    ポート
    0.07
    .bottomAnchor
    0.06
     $(".
    0.06
    "]){↵
    0.06
     $('#
    0.06
    .ISupportInitialize
    0.06
    _kind
    0.06
    ++++++++++++++++
    0.06
    ])(
    0.06
    =sub
    0.06
    Act Density 0.039%

    No Known Activations