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

    Neuronpedia

    INDEX
    Explanations

    trans-earth injection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fructose
    0.41
    dylib
    0.40
    嫖
    0.39
    nipeg
    0.38
    隼
    0.38
     sausage
    0.37
    ገል
    0.37
     Alvaro
    0.37
     Gregg
    0.36
    yno
    0.36
    POSITIVE LOGITS
     earth
    3.70
     Earth
    3.63
    Earth
    3.58
    earth
    3.47
     EARTH
    3.38
     зем
    3.08
    地球
    3.05
     earths
    2.86
     Зем
    2.83
     पृथ्वी
    2.70
    Act Density 0.054%

    No Known Activations