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

    Neuronpedia

    INDEX
    Explanations

    rock formations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stones
    0.66
     stone
    0.65
    STONE
    0.63
     STONE
    0.61
     Stones
    0.60
    Stone
    0.59
     камен
    0.57
     piedra
    0.57
     sandstone
    0.56
    石
    0.56
    POSITIVE LOGITS
    dwelling
    0.45
    diet
    0.42
    mill
    0.42
    hel
    0.40
     Hispan
    0.40
    ah
    0.40
    誨
    0.39
    odata
    0.39
     countrymen
    0.39
    AH
    0.38
    Act Density 0.006%

    No Known Activations