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

    Neuronpedia

    INDEX
    Explanations

    Th1/Th2 balance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     simplest
    -0.08
     Jelly
    -0.07
     Within
    -0.07
     wrap
    -0.07
    wrap
    -0.07
     harga
    -0.07
     dignity
    -0.07
    DNS
    -0.07
     interactive
    -0.07
     DNS
    -0.07
    POSITIVE LOGITS
     predomin
    0.15
     predominant
    0.13
     dominance
    0.12
     favorecer
    0.11
     favoriser
    0.10
     dominant
    0.10
     বেশি
    0.10
     παραγω
    0.10
     privilég
    0.10
     tendency
    0.09
    Act Density 0.016%

    No Known Activations