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

    Neuronpedia

    INDEX
    Explanations

    broken brush, chemical formula

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     neoplas
    0.44
     neuritis
    0.40
     founded
    0.38
    􏰁
    0.38
    water
    0.38
     enteric
    0.38
    eye
    0.37
    iectasis
    0.37
     flora
    0.37
     geology
    0.37
    POSITIVE LOGITS
    航班
    0.45
    这也是
    0.40
    ளையும்
    0.39
    وع
    0.39
     Chavez
    0.39
    гина
    0.39
     Vorteil
    0.39
    妘
    0.38
    Ram
    0.37
    अर
    0.37
    Act Density 0.000%

    No Known Activations