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

    Neuronpedia

    INDEX
    Explanations

    Bh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rest
    -0.07
     squir
    -0.07
    oz
    -0.07
     ],
↵
    -0.07
    搖
    -0.07
    尽力
    -0.07
    不用
    -0.06
    ński
    -0.06
     теат
    -0.06
     fuel
    -0.06
    POSITIVE LOGITS
     Bh
    0.07
    iap
    0.07
    卞
    0.07
    受害
    0.07
    hra
    0.07
    Allowed
    0.07
    лон
    0.07
    .updateDynamic
    0.07
    PYTHON
    0.07
    愍
    0.07
    Act Density 0.011%

    No Known Activations