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

    Neuronpedia

    INDEX
    Explanations

    ancient civilizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aluminium
    -1.03
     electronics
    -0.96
     aluminum
    -0.90
     normally
    -0.88
     parameters
    -0.88
     javax
    -0.86
     after
    -0.86
     November
    -0.86
     november
    -0.85
    十年
    -0.84
    POSITIVE LOGITS
     earliest
    1.83
     ancient
    1.45
     cultures
    1.34
     civilizations
    1.34
     Ancient
    1.31
     древ
    1.26
    odotus
    1.25
    ancient
    1.21
    Ancient
    1.20
     culturas
    1.20
    Act Density 0.164%

    No Known Activations