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

    Neuronpedia

    INDEX
    Explanations

    tribal, aboriginal, indigenous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Butter
    0.42
     butter
    0.42
    ताच
    0.41
    hten
    0.41
    butter
    0.40
     Muh
    0.39
    Butter
    0.38
     mc
    0.35
     cs
    0.34
     مک
    0.34
    POSITIVE LOGITS
     tribal
    1.20
     आदिवासी
    1.08
     Tribal
    1.07
     aboriginal
    0.96
     tribes
    0.93
     Aboriginal
    0.90
    trib
    0.87
     Tribes
    0.86
     जनजाति
    0.85
     trib
    0.84
    Act Density 0.008%

    No Known Activations