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

    Neuronpedia

    INDEX
    Explanations

    Light (literal or metaphorical)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fluid
    -0.09
     fluids
    -0.09
     Fluid
    -0.09
    YN
    -0.08
    Fluid
    -0.08
    haltung
    -0.08
    uffs
    -0.08
     ats
    -0.08
     taxas
    -0.07
     uterus
    -0.07
    POSITIVE LOGITS
     ilum
    0.17
     ilumin
    0.15
     bright
    0.15
     brightly
    0.15
     lumineux
    0.14
    灯
    0.14
     brightest
    0.14
     свет
    0.14
     الضوء
    0.13
     brilh
    0.13
    Act Density 0.065%

    No Known Activations