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

    Neuronpedia

    INDEX
    Explanations

    blo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    集中
    -0.07
    -ion
    -0.07
    完善
    -0.06
    /"
    -0.06
    -n
    -0.06
     magnet
    -0.06
    的感受
    -0.06
    쎗
    -0.06
     remin
    -0.06
     حول
    -0.06
    POSITIVE LOGITS
    ,buf
    0.07
    (grammarAccess
    0.07
    Ϊ
    0.07
    irut
    0.07
    렙
    0.06
    (seg
    0.06
    ocache
    0.06
    DEPTH
    0.06
     Malone
    0.06
    igne
    0.06
    Act Density 1.837%

    No Known Activations