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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    iva
    -0.07
    าะ
    -0.07
    nee
    -0.07
     stands
    -0.07
    olves
    -0.07
     Hotels
    -0.07
    relude
    -0.06
    Books
    -0.06
    יתי
    -0.06
    ={`${
    -0.06
    POSITIVE LOGITS
    MASK
    0.07
    بني
    0.07
    爆料
    0.07
     iterations
    0.07
     estimation
    0.07
    article
    0.07
    䓫
    0.07
    更能
    0.07
    aturated
    0.07
    阿森
    0.07
    Act Density 0.000%

    No Known Activations