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

    Neuronpedia

    INDEX
    Explanations

    countries in geopolitical contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    4
    0.46
    8
    0.44
    6
    0.44
    5
    0.43
    ный
    0.41
    7
    0.40
    ți
    0.39
    น้ำ
    0.38
    mış
    0.38
    实时
    0.38
    POSITIVE LOGITS
     analyze
    0.43
     boulders
    0.41
     ensl
    0.40
     undermine
    0.39
     supremacist
    0.39
     dominance
    0.39
     an
    0.38
     AND
    0.38
     colleges
    0.38
     hurts
    0.38
    Act Density 0.217%

    No Known Activations