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

    Neuronpedia

    INDEX
    Explanations

    military forces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ')↵↵
    -0.08
     unpleasant
    -0.08
    外国
    -0.07
    ди
    -0.07
    .Flat
    -0.07
    zie
    -0.07
    μ
    -0.07
    measurement
    -0.07
    ounds
    -0.07
     ves
    -0.07
    POSITIVE LOGITS
    하여야
    0.07
    .Bold
    0.07
     prom
    0.07
     perman
    0.07
    .Fprintf
    0.07
     attacking
    0.07
     ts
    0.07
    逃跑
    0.07
     logo
    0.07
    столь
    0.06
    Act Density 0.041%

    No Known Activations