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

    Neuronpedia

    INDEX
    Explanations

    九九乘法表

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اطع
    0.78
     Ori
    0.76
     Thorpe
    0.73
    ী
    0.69
    澧
    0.69
    ewalk
    0.67
     Kane
    0.67
    η
    0.67
     Rea
    0.66
     Eri
    0.65
    POSITIVE LOGITS
     Jasmin
    1.19
     Theodore
    1.00
    硅
    0.98
     Kennedy
    0.98
     Jacqueline
    0.97
     Rhonda
    0.94
     Roosevelt
    0.94
     Tatiana
    0.93
    Hydrogen
    0.93
     Brigitte
    0.92
    Act Density 0.659%

    No Known Activations