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

    Neuronpedia

    INDEX
    Explanations

    human service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     वाइ
    0.43
     Cano
    0.38
     Эк
    0.37
     پیک
    0.37
     FRAM
    0.36
    ionali
    0.36
     Energy
    0.35
     Blanchard
    0.35
     Weighted
    0.35
     Yvonne
    0.35
    POSITIVE LOGITS
     নীলন
    0.40
    కుడు
    0.39
     Mohammed
    0.39
     moh
    0.38
    Mohammed
    0.38
     destin
    0.38
    ப்பன்
    0.37
     skillet
    0.37
     placenta
    0.37
     unsaturated
    0.36
    Act Density 0.001%

    No Known Activations