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

    Neuronpedia

    INDEX
    Explanations

    GPS tracking and compare

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Whilst
    0.42
     vasculature
    0.42
    त्री
    0.41
     Whilst
    0.41
    ૐ
    0.40
    Regardless
    0.40
     freighter
    0.38
     그럼
    0.38
    हालांकि
    0.38
    Catagory
    0.37
    POSITIVE LOGITS
     remark
    0.46
    idem
    0.43
    denum
    0.43
    remark
    0.42
     remarks
    0.39
     recuerda
    0.39
    remarkable
    0.38
     excepted
    0.38
     resumed
    0.38
     Remark
    0.38
    Act Density 0.001%

    No Known Activations