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

    Neuronpedia

    INDEX
    Explanations

    th

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     combinations
    -0.07
    posing
    -0.07
     experiences
    -0.07
    "?>↵
    -0.06
    .Decimal
    -0.06
    Av
    -0.06
    .help
    -0.06
     cleanup
    -0.06
    椁
    -0.06
    脓
    -0.06
    POSITIVE LOGITS
     Fayette
    0.07
    _entry
    0.07
     questão
    0.07
    鿍
    0.07
    党风廉政
    0.07
    	state
    0.07
    投资人
    0.07
    释放
    0.07
    فك
    0.06
    分钟左右
    0.06
    Act Density 0.001%

    No Known Activations