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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     descent
    -0.06
     dě
    -0.06
    	Model
    -0.06
    ्रच
    -0.06
     bordered
    -0.06
     cla
    -0.06
    _DETAILS
    -0.06
     troubled
    -0.06
    ودة
    -0.06
    (fm
    -0.06
    POSITIVE LOGITS
     Evans
    0.07
    iless
    0.07
     :]↵
    0.07
     говор
    0.06
    اضی
    0.06
     갤
    0.06
     gà
    0.06
     verdiği
    0.06
    Narr
    0.06
     McGr
    0.06
    Act Density 0.133%

    No Known Activations