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

    Neuronpedia

    INDEX
    Explanations

    snow and ice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eigenstates
    0.41
     Maio
    0.39
     Caedwalla
    0.39
    RegisterClass
    0.39
     eigenvectors
    0.38
    ктором
    0.38
    য়াল
    0.37
     wavefront
    0.37
     tumor
    0.37
    obacillus
    0.37
    POSITIVE LOGITS
     snow
    1.51
    snow
    1.34
    雪
    1.31
    Snow
    1.25
     snowy
    1.24
     Snow
    1.22
     snowfall
    1.22
     雪
    1.20
     winter
    1.19
    ☃
    1.18
    Act Density 0.007%

    No Known Activations