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

    Neuronpedia

    INDEX
    Explanations

    No

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .streaming
    -0.07
    听
    -0.07
    /update
    -0.07
    実は
    -0.07
    寂静
    -0.07
    pool
    -0.07
    資金
    -0.07
     convent
    -0.07
    mute
    -0.06
    _POOL
    -0.06
    POSITIVE LOGITS
    주시
    0.07
    xfff
    0.07
    \Bridge
    0.07
     ↵↵↵↵↵
    0.07
    魉
    0.07
    }')↵↵
    0.06
    主题活动
    0.06
    一定是
    0.06
    .Item
    0.06
    图形
    0.06
    Act Density 0.010%

    No Known Activations