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

    Neuronpedia

    INDEX
    Explanations

    software release notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     रामबा
    0.44
    ams
    0.40
     exactamente
    0.39
    ubah
    0.39
     Min
    0.39
     Mines
    0.39
    uba
    0.38
    README
    0.38
     Dig
    0.38
    ppets
    0.38
    POSITIVE LOGITS
     unwind
    0.45
     entries
    0.43
     chronology
    0.43
     actores
    0.41
     actors
    0.40
     unw
    0.40
    ဠ
    0.40
    መረ
    0.40
    Bedroom
    0.40
     unfiltered
    0.39
    Act Density 0.003%

    No Known Activations