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

    Neuronpedia

    INDEX
    Explanations

    的

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     artifacts
    -0.06
    (mail
    -0.06
     spite
    -0.06
     locksmith
    -0.06
     руч
    -0.06
     locations
    -0.06
    against
    -0.06
    Thumbnail
    -0.06
    Jam
    -0.06
     mov
    -0.06
    POSITIVE LOGITS
    者の
    0.08
    ουσ
    0.08
     '.')
    0.07
    's
    0.07
    스의
    0.07
     greeted
    0.07
     своє
    0.07
    (()=>
    0.07
    'al
    0.07
    гу
    0.07
    Act Density 0.020%

    No Known Activations