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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sizes
    -0.08
    anggal
    -0.06
    \Storage
    -0.06
    parity
    -0.06
     compression
    -0.06
    Ngày
    -0.06
    ��
    -0.06
     měl
    -0.06
    222
    -0.06
    Você
    -0.06
    POSITIVE LOGITS
    UNET
    0.08
     Estr
    0.07
    stract
    0.07
     Fetch
    0.07
    ーネ
    0.06
     Gener
    0.06
     isLoggedIn
    0.06
    .ge
    0.06
     Erect
    0.06
    _"+
    0.06
    Act Density 0.001%

    No Known Activations