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

    Neuronpedia

    INDEX
    Explanations

    delighted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    toHave
    -0.07
    _FOR
    -0.07
    хови
    -0.06
    utan
    -0.06
    InputElement
    -0.06
    {-#
    -0.06
     maple
    -0.06
    byte
    -0.06
    checkbox
    -0.06
     nie
    -0.06
    POSITIVE LOGITS
     pleased
    0.07
     ší
    0.07
     honored
    0.07
     İzmir
    0.06
    層
    0.06
     �
    0.06
    汗
    0.06
     unseren
    0.06
     accol
    0.06
    ).↵↵↵
    0.06
    Act Density 0.018%

    No Known Activations