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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ้าน
    -0.07
     ↵	↵
    -0.07
     mariage
    -0.07
    ract
    -0.07
    Ef
    -0.07
    .Driver
    -0.07
    RAND
    -0.07
    、《
    -0.06
    ""
    -0.06
    +"'
    -0.06
    POSITIVE LOGITS
     pointers
    0.07
    比例
    0.06
    sil
    0.06
    tas
    0.06
     TValue
    0.06
     depending
    0.06
    Props
    0.06
    [np
    0.06
    웅
    0.06
     TW
    0.05
    Act Density 0.002%

    No Known Activations