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

    Neuronpedia

    INDEX
    Explanations

    't

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tar
    -0.07
     Remember
    -0.07
    Hu
    -0.06
    再
    -0.06
     dư
    -0.06
     вов
    -0.06
    уйте
    -0.06
    ド
    -0.06
    ض
    -0.06
     примерно
    -0.05
    POSITIVE LOGITS
     fisheries
    0.07
     xxx
    0.06
    ışı
    0.06
    ubbles
    0.06
    -property
    0.06
    	float
    0.06
     Sunshine
    0.06
     日本
    0.06
    ":"+
    0.06
     자동
    0.06
    Act Density 0.000%

    No Known Activations