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

    Neuronpedia

    INDEX
    Explanations

    necessary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Thêm
    -0.07
     envy
    -0.07
     dac
    -0.06
     GMC
    -0.06
     nâng
    -0.06
     pud
    -0.06
    版
    -0.06
     IDC
    -0.06
    dp
    -0.06
    _choice
    -0.06
    POSITIVE LOGITS
    リン
    0.07
    ываем
    0.06
     한국
    0.06
    uele
    0.06
     péri
    0.06
    has
    0.06
    (["
    0.06
     слож
    0.06
     
    0.06
     sidel
    0.06
    Act Density 0.021%

    No Known Activations