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

    Neuronpedia

    INDEX
    Explanations

    ownership, responsibility, problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    »،
    0.46
    丶
    0.46
    購物
    0.46
    »:
    0.45
    涪
    0.42
     Nghị
    0.42
    剡
    0.41
     യുവ
    0.41
    并不是
    0.41
    便捷
    0.40
    POSITIVE LOGITS
     supervised
    0.48
     управля
    0.46
     arrow
    0.43
     by
    0.42
     sponsored
    0.42
     think
    0.42
    arrow
    0.42
     evenings
    0.41
     none
    0.41
     अध्यक्षता
    0.41
    Act Density 0.000%

    No Known Activations