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

    Neuronpedia

    INDEX
    Explanations

    names and film credits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     liking
    -0.08
     новые
    -0.07
    انیا
    -0.07
    unga
    -0.07
    iplinary
    -0.07
     공간
    -0.07
     '-',
    -0.07
    άντα
    -0.06
    LAND
    -0.06
     uv
    -0.06
    POSITIVE LOGITS
    739
    0.06
    Repair
    0.06
    .Misc
    0.06
    .vo
    0.06
    ่
    0.06
    .getIn
    0.06
    �
    0.05
    邮箱
    0.05
    /dd
    0.05
    ーブ
    0.05
    Act Density 0.012%

    No Known Activations