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

    Neuronpedia

    INDEX
    Explanations

    interference with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     çiz
    -0.07
    пря
    -0.07
    喀
    -0.07
    �
    -0.07
    ..."↵
    -0.07
    升起
    -0.07
    驶
    -0.06
     ölçü
    -0.06
    Miss
    -0.06
    Map
    -0.06
    POSITIVE LOGITS
    묠
    0.07
    版权声明
    0.07
    .prod
    0.07
    .RELATED
    0.07
    ])))↵
    0.07
    equality
    0.07
    娱
    0.06
     Desktop
    0.06
    _FC
    0.06
    Normally
    0.06
    Act Density 0.004%

    No Known Activations