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

    Neuronpedia

    INDEX
    Explanations

    sequence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     též
    -0.07
    chestra
    -0.07
     nhằm
    -0.06
    アー
    -0.06
    CATEGORY
    -0.06
    .SizeType
    -0.06
     몸을
    -0.06
    Ｙ
    -0.06
    VERN
    -0.06
    닉
    -0.06
    POSITIVE LOGITS
     broke
    0.07
     Christopher
    0.06
     meetings
    0.06
    references
    0.06
     escalation
    0.06
    _MORE
    0.06
    /Image
    0.06
     apples
    0.06
     thereafter
    0.06
     Scott
    0.06
    Act Density 0.019%

    No Known Activations