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

    Neuronpedia

    INDEX
    Explanations

    guilty

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -turned
    -0.08
    而是
    -0.07
    EMA
    -0.07
     wiki
    -0.07
    雇佣
    -0.07
    璐
    -0.07
     Mona
    -0.07
    峡谷
    -0.07
    海拔
    -0.07
     blog
    -0.06
    POSITIVE LOGITS
    وفق
    0.07
     jylland
    0.07
    安全感
    0.07
    (newState
    0.07
    �
    0.07
    隔音
    0.07
    greater
    0.07
     sendData
    0.06
     gj
    0.06
    便于
    0.06
    Act Density 0.003%

    No Known Activations