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

    Neuronpedia

    INDEX
    Explanations

    Technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    伯
    -0.07
    ुकस
    -0.06
    樹
    -0.06
    aincontri
    -0.06
    anker
    -0.06
    諾
    -0.06
     nood
    -0.06
    ,G
    -0.06
    ):
    -0.06
    grading
    -0.06
    POSITIVE LOGITS
     FOX
    0.06
     peeled
    0.06
    ristol
    0.06
    logue
    0.06
     una
    0.06
    이가
    0.06
    ﻟ�
    0.06
    onym
    0.06
    deck
    0.06
     Fence
    0.06
    Act Density 0.000%

    No Known Activations