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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     प्रशासन
    -0.09
     juggling
    -0.08
    â
    -0.08
    Monkey
    -0.08
     deadlines
    -0.08
     отмен
    -0.08
     Administration
    -0.08
     disability
    -0.08
     careg
    -0.08
     mentally
    -0.08
    POSITIVE LOGITS
     predomin
    0.10
     dominated
    0.10
     dominant
    0.10
     neon
    0.10
     dominance
    0.10
     dielectric
    0.09
     الكيمي
    0.09
     coolant
    0.09
    浓
    0.09
     পৃথিব
    0.09
    Act Density 0.008%

    No Known Activations