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

    Neuronpedia

    INDEX
    Explanations

    expensive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     maritime
    -0.08
    mit
    -0.07
    at
    -0.07
     pier
    -0.07
    2
    -0.07
     Circle
    -0.06
    beat
    -0.06
     lecturer
    -0.06
     Channel
    -0.06
     nat
    -0.06
    POSITIVE LOGITS
     expensive
    0.14
     inexpensive
    0.11
     expenses
    0.08
     frente
    0.07
     ansch
    0.07
     Expenses
    0.07
     espan
    0.07
    скому
    0.07
     inexp
    0.07
     inne
    0.07
    Act Density 0.008%

    No Known Activations