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

    Neuronpedia

    INDEX
    Explanations

    Output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    incorpor
    0.57
    用い
    0.52
    proposed
    0.50
    Sne
    0.50
    课题
    0.50
     postulated
    0.50
    circuit
    0.49
     kial
    0.49
    ordinating
    0.49
    മ്പി
    0.48
    POSITIVE LOGITS
     Notice
    0.69
     NOTICE
    0.66
     ไม่มี
    0.66
     Thanks
    0.64
     没有
    0.64
     Lovely
    0.63
     Waalaikumsalam
    0.62
     老
    0.62
     gcc
    0.62
     输出
    0.61
    Act Density 0.449%

    No Known Activations