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

    Neuronpedia

    INDEX
    Explanations

    action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rằng
    -0.07
    呼ば
    -0.06
    (det
    -0.06
    ，则
    -0.06
    テ
    -0.06
    ğinden
    -0.06
    ，因为
    -0.06
    (mock
    -0.06
     liệu
    -0.06
     chall
    -0.06
    POSITIVE LOGITS
    +i
    0.07
    iction
    0.07
     Sunni
    0.07
     oppress
    0.07
     succession
    0.06
    -regexp
    0.06
    horizontal
    0.06
    .less
    0.06
     suits
    0.06
    gam
    0.06
    Act Density 0.007%

    No Known Activations