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

    Neuronpedia

    INDEX
    Explanations

    or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     That
    0.92
    8
    0.88
     THAT
    0.88
     {
    0.84
     ۸
    0.84
     for
    0.82
     conness
    0.82
    6
    0.82
     This
    0.81
     biofilms
    0.81
    POSITIVE LOGITS
    または
    0.98
     లేదా
    0.90
    z
    0.86
     hoặc
    0.85
     ή
    0.84
    b
    0.82
     или
    0.82
    gelijk
    0.81
    fyp
    0.81
     veya
    0.80
    Act Density 0.211%

    No Known Activations