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

    Neuronpedia

    INDEX
    Explanations

    court cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Seoul
    -0.07
     Abe
    -0.07
    廟
    -0.07
    advance
    -0.07
    国务院
    -0.07
    箸
    -0.07
    煮
    -0.07
    教育部
    -0.07
    (savedInstanceState
    -0.07
     Volkswagen
    -0.07
    POSITIVE LOGITS
     GF
    0.07
    냑
    0.07
     ec
    0.07
    月中旬
    0.07
     substit
    0.07
     VALUE
    0.07
     выз
    0.07
    磲
    0.07
    ialias
    0.07
    tório
    0.07
    Act Density 0.001%

    No Known Activations